Michael M. Bronstein — accepted AI-conference papers

2026

Attention Sinks and Compression Valleys in LLMs are Two Sides of the Same Coin

Enrique Queipo-de-Llano, Alvaro Arroyo, Federico Barbero, Xiaowen Dong, Michael M. Bronstein, Yann LeCun +1

ICLR 2026poster

Attention sinks and compression valleys have attracted significant attention as two puzzling phenomena in large language models, but have been studied in isolation. In this work, we present a surprising connection between attention sinks and compression valleys, tracing both to the formation of mass…

Cited by 0 Source ↗Scholar ↗

2026

Carré du champ flow matching: better quality-generalisation tradeoff in generative models

Jacob Bamberger, Iolo Jones, Dennis Duncan, Michael M. Bronstein, Pierre Vandergheynst, Adam Gosztolai

ICLR 2026poster

Deep generative models often face a fundamental tradeoff: high sample quality can come at the cost of memorisation, where the model reproduces training data rather than generalising across the underlying data geometry. We introduce Carré du champ flow matching (CDC-FM), a generalisation of flow matc…

Cited by 0 Source ↗Scholar ↗

2026

Efficient Learning on Large Graphs using a Densifying Regularity Lemma

Jonathan Kouchly, Ben Finkelshtein, Michael M. Bronstein, Ron Levie

ICLR 2026poster

Learning on large graphs presents significant challenges, with traditional Message Passing Neural Networks suffering from computational and memory costs scaling linearly with the number of edges. We introduce the Intersecting Block Graph (IBG), a low-rank factorization of large directed graphs based…

Cited by 0 Source ↗Scholar ↗

2026

Efficient Regression-based Training of Normalizing Flows for Boltzmann Generators

Danyal Rehman, Oscar Davis, Jiarui Lu, Jian Tang, Michael M. Bronstein, Yoshua Bengio +2

ICLR 2026poster

Simulation-free training frameworks have been at the forefront of the generative modelling revolution in continuous spaces, leading to large-scale diffusion and flow matching models. However, such modern generative models suffer from expensive inference, inhibiting their use in numerous scientific a…

Cited by 0 Source ↗code ↗Scholar ↗

2026

Flock: A Knowledge Graph Foundation Model via Learning on Random Walks

Jinwoo Kim, Xingyue Huang, Krzysztof Olejniczak, Kyungbin Min, Michael M. Bronstein, Seunghoon Hong +1

ICLR 2026poster

We study the problem of zero-shot link prediction on knowledge graphs (KGs), which requires models to generalize to novel entities and novel relations. Knowledge graph foundation models (KGFMs) address this task by enforcing equivariance over both nodes and relations, which enables them to learn str…

Cited by 0 Source ↗code ↗Scholar ↗

2026

Generalised Flow Maps for Few-Step Generative Modelling on Riemannian Manifolds

Oscar Davis, Michael Samuel Albergo, Nicholas Matthew Boffi, Michael M. Bronstein, Joey Bose

ICLR 2026poster

Geometric data and purpose-built generative models on them have become ubiquitous in high-impact deep learning application domains, ranging from protein backbone generation and computational chemistry to geospatial data. Current geometric generative models remain computationally expensive at infer…

Cited by 0 Source ↗code ↗Scholar ↗

2026

HYPER: A Foundation Model for Inductive Link Prediction with Knowledge Hypergraphs

Xingyue Huang, Mikhail Galkin, Michael M. Bronstein, Ismail Ilkan Ceylan

ICLR 2026poster

Inductive link prediction with knowledge hypergraphs is the task of predicting missing hyperedges involving completely *novel entities* (i.e., nodes unseen during training). Existing methods for inductive link prediction with knowledge hypergraphs assume a fixed relational vocabulary and, as a resul…

Cited by 0 Source ↗code ↗Scholar ↗

2026

LLMs Can Hide Text in Other Text of the Same Length

Antonio Norelli, Michael M. Bronstein

ICLR 2026poster

A meaningful text can be hidden inside another, completely different yet still coherent and plausible, text of the same length. For example, a tweet containing a harsh political critique could be embedded in a tweet that celebrates the same political leader, or an ordinary product review could conce…

Cited by 0 Source ↗code ↗Scholar ↗

2026

Learning Escorted Protocols For Multistate Free-Energy Estimation

Lars Holdijk, Nithishwer Mouroug Anand, Michael M. Bronstein, Max Welling

ICLR 2026poster

Estimating relative free energy differences between multiple thermodynamic states lies at the core of numerous problems in computational biochemistry. Traditional estimators, such as Free Energy Perturbation and its non-equilibrium counterpart based on the Jarzynski equality, rely on defining a swit…

Cited by 0 Source ↗Scholar ↗

2026

MarS-FM: Generative Modeling of Molecular Dynamics via Markov State Models

Kacper Kapuśniak, Cristian Gabellini, Michael M. Bronstein, Prudencio Tossou, Francesco Di Giovanni

ICLR 2026poster

Molecular Dynamics (MD) is a powerful computational microscope for probing protein functions. However, the need for fine-grained integration and the long timescales of biomolecular events make MD computationally expensive. To address this, several generative models have been proposed to generate sur…

Cited by 0 Source ↗code ↗Scholar ↗

2026

OXtal: An All-Atom Diffusion Model for Organic Crystal Structure Prediction

Emily Jin, Andrei Cristian Nica, Kin Long Kelvin Lee, Joey Bose, Mikhail Galkin, Santiago Miret +5

ICLR 2026poster

Accurately predicting experimentally-realizable $3\textrm{D}$ molecular crystal structures from their $2\textrm{D}$ chemical graphs is a long-standing open challenge in computational chemistry called $\textit{crystal structure prediction}$ (CSP). Efficiently solving this problem has implications ran…

Cited by 0 Source ↗Scholar ↗

2026

Planner Aware Path Learning in Diffusion Language Models Training

Fred Zhangzhi Peng, Zachary Bezemek, Jarrid Rector-Brooks, Shuibai Zhang, Michael M. Bronstein, Anru Zhang +2

ICLR 2026oral

Diffusion language models have emerged as a powerful alternative to autoregressive models, enabling fast inference through more flexible and parallel generation paths. This flexibility of sampling is unlocked by new engineered sampling strategies, or *planners*, that select more favorable generation…

Cited by 13 Source ↗code ↗Scholar ↗

2026

ResCP: Reservoir Conformal Prediction for Time Series Forecasting

Roberto Neglia, Andrea Cini, Michael M. Bronstein, Filippo Maria Bianchi

ICLR 2026poster

Conformal prediction offers a powerful framework for building distribution-free prediction intervals for exchangeable data. Existing methods that extend conformal prediction to sequential data rely on fitting a relatively complex model to capture temporal dependencies. However, these metho…

Cited by 0 Source ↗code ↗Scholar ↗

2026

Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time Compute

Kieran Didi, Zuobai Zhang, Guoqing Zhou, Danny Reidenbach, Zhonglin Cao, Sooyoung Cha +8

ICLR 2026oral

Protein interaction modeling is central to protein design, which has been transformed by machine learning with broad applications in drug discovery and beyond. In this landscape, structure-based de novo binder design is most often cast as either conditional generative modeling or sequence optimizati…

Cited by 0 Source ↗code ↗Scholar ↗

2026

TGM: A Modular and Efficient Library for Machine Learning on Temporal Graphs

Jacob Chmura, Shenyang Huang, Tran Gia Bao Ngo, Ali Parviz, Farimah Poursafaei, Jure Leskovec +4

ICLR 2026poster

Well-designed open-source software drives progress in Machine Learning (ML) research. While static graph ML enjoys mature frameworks like PyTorch Geometric and DGL, ML for temporal graphs (TG), networks that evolve over time, lacks comparable infrastructure. Existing TG libraries are often tailored…

Cited by 0 Source ↗code ↗Scholar ↗

2026

Towards Quantifying Long-Range Interactions in Graph Machine Learning: a Large Graph Dataset and a Measurement

Huidong Liang, Haitz Sáez de Ocáriz Borde, Baskaran Sripathmanathan, Michael M. Bronstein, Xiaowen Dong

ICLR 2026poster

Long-range dependencies are critical for effective graph representation learning, yet most existing datasets focus on small graphs tailored to inductive tasks, offering limited insight into long-range interactions. Current evaluations primarily compare models employing global attention (e.g., graph…

Cited by 0 Source ↗code ↗Scholar ↗

2026

gLSTM: Mitigating Over-Squashing by Increasing Storage Capacity

Hugh Blayney, Alvaro Arroyo, Xiaowen Dong, Michael M. Bronstein

ICLR 2026poster

Graph Neural Networks (GNNs) leverage the graph structure to transmit information between nodes, typically through the message-passing mechanism. While these models have found a wide variety of applications, they are known to suffer from over-squashing, where information from a large receptive field…

Cited by 0 Source ↗code ↗Scholar ↗

2025

A General Graph Spectral Wavelet Convolution via Chebyshev Order Decomposition

Nian Liu, Xiaoxin He, Thomas Laurent, Francesco Di Giovanni, Michael M. Bronstein, Xavier Bresson

ICML 2025poster

Spectral graph convolution, an important tool of data filtering on graphs, relies on two essential decisions: selecting spectral bases for signal transformation and parameterizing the kernel for frequency analysis. While recent techniques mainly focus on standard Fourier transform and vector-valued…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

Amortized Sampling with Transferable Normalizing Flows

Charlie B. Tan, Majdi Hassan, Leon Klein, Saifuddin Syed, Dominique Beaini, Michael M. Bronstein +2

NeurIPS 2025poster

Efficient equilibrium sampling of molecular conformations remains a core challenge in computational chemistry and statistical inference. Classical approaches such as molecular dynamics or Markov chain Monte Carlo inherently lack amortization; the computational cost of sampling must be paid in-full f…

Cited by 0 Source ↗Scholar ↗

2025

Balancing Efficiency and Expressiveness: Subgraph GNNs with Walk-Based Centrality

Joshua Southern, Yam Eitan, Guy Bar-Shalom, Michael M. Bronstein, Haggai Maron, Fabrizio Frasca

ICML 2025poster

Subgraph GNNs have emerged as promising architectures that overcome the expressiveness limitations of Graph Neural Networks (GNNs) by processing bags of subgraphs. Despite their compelling empirical performance, these methods are afflicted by a high computational complexity: they process bags whose…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

Bundle Neural Network for message diffusion on graphs

Jacob Bamberger, Federico Barbero, Xiaowen Dong, Michael M. Bronstein

ICLR 2025spotlight

The dominant paradigm for learning on graphs is message passing. Despite being a strong inductive bias, the local message passing mechanism faces challenges such as over-smoothing, over-squashing, and limited expressivity. To address these issues, we introduce Bundle Neural Networks (BuNNs), a novel…

Cited by 1 Source ↗PDF ↗Scholar ↗

2025

Curly Flow Matching for Learning Non-gradient Field Dynamics

Katarina Petrović, Lazar Atanackovic, Viggo Moro, Kacper Kapuśniak, Ismail Ilkan Ceylan, Michael M. Bronstein +2

NeurIPS 2025poster

Modeling the transport dynamics of natural processes from population-level observations is a ubiquitous problem in the natural sciences. Such models rely on key assumptions about the underlying process in order to enable faithful learning of governing dynamics that mimic the actual system behavior.…

Cited by 0 Source ↗code ↗Scholar ↗

2025

Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights

Zhiyuan Liang, Dongwen Tang, Yuhao Zhou, Xuanlei Zhao, Mingjia Shi, Wangbo Zhao +8

NeurIPS 2025poster

Modern Parameter-Efficient Fine-Tuning (PEFT) methods such as low-rank adaptation (LoRA) reduce the cost of customizing large language models (LLMs), yet still require a separate optimization run for every downstream dataset. We introduce \textbf{Drag-and-Drop LLMs (\textit{DnD})}, a prompt-conditio…

Cited by 0 Source ↗code ↗Scholar ↗

2025

Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models

Ben Finkelshtein, Ismail Ilkan Ceylan, Michael M. Bronstein, Ron Levie

NeurIPS 2025poster

Graph machine learning architectures are typically tailored to specific tasks on specific datasets, which hinders their broader applicability. This has led to a new quest in graph machine learning: \emph{how to build graph foundation models (GFMs)} capable of generalizing across arbitrary graphs an…

Cited by 0 Source ↗code ↗Scholar ↗

2025

Fully-inductive Node Classification on Arbitrary Graphs

Jianan Zhao, Zhaocheng Zhu, Mikhail Galkin, Hesham Mostafa, Michael M. Bronstein, Jian Tang

ICLR 2025poster

One fundamental challenge in graph machine learning is generalizing to new graphs. Many existing methods following the inductive setup can generalize to test graphs with new structures, but assuming the feature and label spaces remain the same as the training ones. This paper introduces a fully-ind…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2025

GradMetaNet: An Equivariant Architecture for Learning on Gradients

Yoav Gelberg, Yam Eitan, Aviv Navon, Aviv Shamsian, Theo Putterman, Michael M. Bronstein +1

NeurIPS 2025poster

Gradients of neural networks encode valuable information for optimization, editing, and analysis of models. Therefore, practitioners often treat gradients as inputs to task-specific algorithms, e.g., using gradient statistics for pruning or optimization. Recent works explore *learning* algorithms th…

Cited by 0 Source ↗Scholar ↗

2025

Gradient Variance Reveals Failure Modes in Flow-Based Generative Models

Teodora Reu, Sixtine Dromigny, Michael M. Bronstein, Francisco Vargas

NeurIPS 2025spotlight

Rectified Flows learn ODE vector fields whose trajectories are straight between source and target distributions, enabling near one-step inference. We show that this straight-path objective reveals fundamental failure modes: under deterministic training, low gradient variance drives memorization of a…

Cited by 0 Source ↗Scholar ↗

2025

Homomorphism Counts as Structural Encodings for Graph Learning

Linus Bao, Emily Jin, Michael M. Bronstein, Ismail Ilkan Ceylan, Matthias Lanzinger

ICLR 2025poster

Graph Transformers are popular neural networks that extend the well-known Transformer architecture to the graph domain. These architectures operate by applying self-attention on graph nodes and incorporating graph structure through the use of positional encodings (e.g., Laplacian positional encoding…

Cited by 0 Source ↗PDF ↗code ↗Scholar ↗

2025

How Expressive are Knowledge Graph Foundation Models?

Xingyue Huang, Pablo Barcelo, Michael M. Bronstein, Ismail Ilkan Ceylan, Mikhail Galkin, Juan L Reutter +1

ICML 2025poster

Knowledge Graph Foundation Models (KGFMs) are at the frontier for deep learning on knowledge graphs (KGs), as they can generalize to completely novel knowledge graphs with different relational vocabularies. Despite their empirical success, our theoretical understanding of KGFMs remains very limited.…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Multi-domain Distribution Learning for De Novo Drug Design

Arne Schneuing, Ilia Igashov, Adrian W. Dobbelstein, Thomas Castiglione, Michael M. Bronstein, Bruno Correia

ICLR 2025poster

We introduce DrugFlow, a generative model for structure-based drug design that integrates continuous flow matching with discrete Markov bridges, demonstrating state-of-the-art performance in learning chemical, geometric, and physical aspects of three-dimensional protein-ligand data. We endow DrugFlo…

Cited by 1 Source ↗PDF ↗Scholar ↗

2025

Neural Spacetimes for DAG Representation Learning

Haitz Sáez de Ocáriz Borde, Anastasis Kratsios, Marc T. Law, Xiaowen Dong, Michael M. Bronstein

ICLR 2025poster

We propose a class of trainable deep learning-based geometries called Neural SpaceTimes (NSTs), which can universally represent nodes in weighted Directed Acyclic Graphs (DAGs) as events in a spacetime manifold. While most works in the literature focus on undirected graph representation learning or…

Cited by 1 Source ↗PDF ↗Scholar ↗

2025

On Measuring Long-Range Interactions in Graph Neural Networks

Jacob Bamberger, Benjamin Gutteridge, Scott le Roux, Michael M. Bronstein, Xiaowen Dong

ICML 2025poster

Long-range graph tasks --- those dependent on interactions between `distant' nodes --- are an open problem in graph neural network research. Real-world benchmark tasks, especially the Long Range Graph Benchmark, have become popular for validating the long-range capability of proposed architectures.…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learning

Alvaro Arroyo, Alessio Gravina, Benjamin Gutteridge, Federico Barbero, Claudio Gallicchio, Xiaowen Dong +2

NeurIPS 2025poster

Graph Neural Networks (GNNs) are models that leverage the graph structure to transmit information between nodes, typically through the message-passing operation. While widely successful, this approach is well-known to suffer from representational collapse as the number of layers increases and insens…

Cited by 0 Source ↗Scholar ↗

2025

Over-squashing in Spatiotemporal Graph Neural Networks

Ivan Marisca, Jacob Bamberger, Cesare Alippi, Michael M. Bronstein

NeurIPS 2025poster

Graph Neural Networks (GNNs) have achieved remarkable success across various domains. However, recent theoretical advances have identified fundamental limitations in their information propagation capabilities, such as over-squashing, where distant nodes fail to effectively exchange information. Whil…

Cited by 0 Source ↗Scholar ↗

2025

Position: Graph Learning Will Lose Relevance Due To Poor Benchmarks

Maya Bechler-Speicher, Ben Finkelshtein, Fabrizio Frasca, Luis Müller, Jan Tönshoff, Antoine Siraudin +6

ICML 2025poster

While machine learning on graphs has demonstrated promise in drug design and molecular property prediction, significant benchmarking challenges hinder its further progress and relevance. Current benchmarking practices often lack focus on transformative, real-world applications, favoring narrow domai…

Cited by 1 Source ↗PDF ↗Scholar ↗

2025

Progressive Inference-Time Annealing of Diffusion Models for Sampling from Boltzmann Densities

Tara Akhound-Sadegh, Jungyoon Lee, Joey Bose, Valentin De Bortoli, Arnaud Doucet, Michael M. Bronstein +4

NeurIPS 2025spotlight

Sampling efficiently from a target unnormalized probability density remains a core challenge, with relevance across countless high-impact scientific applications. A promising approach towards this challenge is the design of amortized samplers that borrow key ideas, such as probability path design, f…

Cited by 0 Source ↗Scholar ↗

2025

Scalable Equilibrium Sampling with Sequential Boltzmann Generators

Charlie B. Tan, Joey Bose, Chen Lin, Leon Klein, Michael M. Bronstein, Alexander Tong

ICML 2025poster

Scalable sampling of molecular states in thermodynamic equilibrium is a long-standing challenge in statistical physics. Boltzmann generators tackle this problem by pairing normalizing flows with importance sampling to obtain uncorrelated samples under the target distribution. In this paper, we exten…

Cited by 2 Source ↗PDF ↗Scholar ↗

2025

Steering Masked Discrete Diffusion Models via Discrete Denoising Posterior Prediction

Jarrid Rector-Brooks, Mohsin Hasan, Zhangzhi Peng, Cheng-Hao Liu, Sarthak Mittal, Nouha Dziri +4

ICLR 2025poster

Generative modeling of discrete data underlies important applications spanning text-based agents like ChatGPT to the design of the very building blocks of life in protein sequences. However, application domains need to exert control over the generated data by steering the generative process—typicall…

Cited by 8 Source ↗PDF ↗Scholar ↗

2025

Supercharging Graph Transformers with Advective Diffusion

Qitian Wu, Chenxiao Yang, Kaipeng Zeng, Michael M. Bronstein

ICML 2025poster

The capability of generalization is a cornerstone for the success of modern learning systems. For non-Euclidean data, e.g., graphs, that particularly involves topological structures, one important aspect neglected by prior studies is how machine learning models generalize under topological shifts. T…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity

Yam Eitan, Yoav Gelberg, Guy Bar-Shalom, Fabrizio Frasca, Michael M. Bronstein, Haggai Maron

ICLR 2025oral

Topological deep learning (TDL) is a rapidly growing field that seeks to leverage topological structure in data and facilitate learning from data supported on topological objects, ranging from molecules to 3D shapes. Most TDL architectures can be unified under the framework of higher-order message-p…

Cited by 8 Source ↗PDF ↗code ↗Scholar ↗

2025

Understanding Virtual Nodes: Oversquashing and Node Heterogeneity

Joshua Southern, Francesco Di Giovanni, Michael M. Bronstein, Johannes F. Lutzeyer

ICLR 2025poster

While message passing neural networks (MPNNs) have convincing success in a range of applications, they exhibit limitations such as the oversquashing problem and their inability to capture long-range interactions. Augmenting MPNNs with a virtual node (VN) removes the locality constraint of the layer…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Cooperative Graph Neural Networks

Ben Finkelshtein, Xingyue Huang, Michael M. Bronstein, Ismail Ilkan Ceylan

ICML 2024poster

Graph neural networks are popular architectures for graph machine learning, based on iterative computation of node representations of an input graph through a series of invariant transformations. A large class of graph neural networks follow a standard message-passing paradigm: at every layer, each…

Cited by 25 Source ↗PDF ↗code ↗Scholar ↗

2024

Fisher Flow Matching for Generative Modeling over Discrete Data

Oscar Davis, Samuel Kessler, Mircea Petrache, Ismail Ilkan Ceylan, Michael M. Bronstein, Joey Bose

NeurIPS 2024poster

Generative modeling over discrete data has recently seen numerous success stories, with applications spanning language modeling, biological sequence design, and graph-structured molecular data. The predominant generative modeling paradigm for discrete data is still autoregressive, with more recent a…

Cited by 15 Source ↗PDF ↗Scholar ↗

2024

From Latent Graph to Latent Topology Inference: Differentiable Cell Complex Module

Claudio Battiloro, Indro Spinelli, Lev Telyatnikov, Michael M. Bronstein, Simone Scardapane, Paolo Di Lorenzo

ICLR 2024poster

Latent Graph Inference (LGI) relaxed the reliance of Graph Neural Networks (GNNs) on a given graph topology by dynamically learning it. However, most of LGI methods assume to have a (noisy, incomplete, improvable, ...) input graph to rewire and can solely learn regular graph topologies. In the wake…

Cited by 20 Source ↗PDF ↗Scholar ↗

2024

Homomorphism Counts for Graph Neural Networks: All About That Basis

Emily Jin, Michael M. Bronstein, Ismail Ilkan Ceylan, Matthias Lanzinger

ICML 2024poster

A large body of work has investigated the properties of graph neural networks and identified several limitations, particularly pertaining to their expressive power. Their inability to count certain *patterns* (e.g., cycles) in a graph lies at the heart of such limitations, since many functions to be…

Cited by 9 Source ↗PDF ↗Scholar ↗

2024

Learning on Large Graphs using Intersecting Communities

Ben Finkelshtein, Ismail Ilkan Ceylan, Michael M. Bronstein, Ron Levie

NeurIPS 2024poster

Message Passing Neural Networks (MPNNs) are a staple of graph machine learning. MPNNs iteratively update each node’s representation in an input graph by aggregating messages from the node’s neighbors, which necessitates a memory complexity of the order of the __number of graph edges__. This complexi…

Cited by 5 Source ↗PDF ↗code ↗Scholar ↗

2024

Locality-Aware Graph Rewiring in GNNs

Federico Barbero, Ameya Velingker, Amin Saberi, Michael M. Bronstein, Francesco Di Giovanni

ICLR 2024poster

Graph Neural Networks (GNNs) are popular models for machine learning on graphs that typically follow the message-passing paradigm, whereby the feature of a node is updated recursively upon aggregating information over its neighbors. While exchanging messages over the input graph endows GNNs with a s…

Cited by 29 Source ↗PDF ↗Scholar ↗

2024

Metric Flow Matching for Smooth Interpolations on the Data Manifold

Kacper Kapusniak, Peter Potaptchik, Teodora Reu, Leo Zhang, Alexander Tong, Michael M. Bronstein +2

NeurIPS 2024poster

Matching objectives underpin the success of modern generative models and rely on constructing conditional paths that transform a source distribution into a target distribution. Despite being a fundamental building block, conditional paths have been designed principally under the assumption of $\text…

Cited by 15 Source ↗PDF ↗code ↗Scholar ↗

2024

On the Limitations of Fractal Dimension as a Measure of Generalization

Charlie Tan, Inés García-Redondo, Qiquan Wang, Michael M. Bronstein, Anthea Monod

NeurIPS 2024poster

Bounding and predicting the generalization gap of overparameterized neural networks remains a central open problem in theoretical machine learning. There is a recent and growing body of literature that proposes the framework of fractals to model optimization trajectories of neural networks, motivati…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2024

Position: Future Directions in the Theory of Graph Machine Learning

Christopher Morris, Fabrizio Frasca, Nadav Dym, Haggai Maron, Ismail Ilkan Ceylan, Ron Levie +4

ICML 2024poster

Machine learning on graphs, especially using graph neural networks (GNNs), has seen a surge in interest due to the wide availability of graph data across a broad spectrum of disciplines, from life to social and engineering sciences. Despite their practical success, our theoretical understanding of t…

Cited by 14 Source ↗PDF ↗Scholar ↗

2024

Position: Topological Deep Learning is the New Frontier for Relational Learning

Theodore Papamarkou, Tolga Birdal, Michael M. Bronstein, Gunnar E. Carlsson, Justin Curry, Yue Gao +16

ICML 2024poster

Topological deep learning (TDL) is a rapidly evolving field that uses topological features to understand and design deep learning models. This paper posits that TDL is the new frontier for relational learning. TDL may complement graph representation learning and geometric deep learning by incorporat…

Cited by 40 Source ↗PDF ↗Scholar ↗

2024

RetroBridge: Modeling Retrosynthesis with Markov Bridges

Ilia Igashov, Arne Schneuing, Marwin Segler, Michael M. Bronstein, Bruno Correia

ICLR 2024spotlight

Retrosynthesis planning is a fundamental challenge in chemistry which aims at designing multi-step reaction pathways from commercially available starting materials to a target molecule. Each step in multi-step retrosynthesis planning requires accurate prediction of possible precursor molecules given…

Cited by 28 Source ↗PDF ↗code ↗Scholar ↗

2024

SE(3)-Stochastic Flow Matching for Protein Backbone Generation

Joey Bose, Tara Akhound-Sadegh, Guillaume Huguet, Kilian FATRAS, Jarrid Rector-Brooks, Cheng-Hao Liu +4

ICLR 2024spotlight

The computational design of novel protein structures has the potential to impact numerous scientific disciplines greatly. Toward this goal, we introduce \foldflow, a series of novel generative models of increasing modeling power based on the flow-matching paradigm over $3\mathrm{D}$ rigid motions---…

Cited by 76 Source ↗PDF ↗code ↗Scholar ↗

2024

Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Generation

Guillaume Huguet, James Vuckovic, Kilian FATRAS, Eric Thibodeau-Laufer, Pablo Lemos, Riashat Islam +6

NeurIPS 2024poster

Proteins are essential for almost all biological processes and derive their diverse functions from complex $3 \rm D$ structures, which are in turn determined by their amino acid sequences. In this paper, we exploit the rich biological inductive bias of amino acid sequences and introduce FoldFlow++,…

Cited by 31 Source ↗PDF ↗Scholar ↗

2023

Curvature Filtrations for Graph Generative Model Evaluation

Joshua Southern, Jeremy Wayland, Michael M. Bronstein, Bastian Rieck

NeurIPS 2023poster

Graph generative model evaluation necessitates understanding differences between graphs on the distributional level. This entails being able to harness salient attributes of graphs in an efficient manner. Curvature constitutes one such property of graphs, and has recently started to prove useful in…

Cited by 21 Source ↗PDF ↗code ↗Scholar ↗

2023

DRew: Dynamically Rewired Message Passing with Delay

Benjamin Gutteridge, Xiaowen Dong, Michael M. Bronstein, Francesco Di Giovanni

ICML 2023poster

Message passing neural networks (MPNNs) have been shown to suffer from the phenomenon of over-squashing that causes poor performance for tasks relying on long-range interactions. This can be largely attributed to message passing only occurring locally, over a node's immediate neighbours. Rewiring ap…

Cited by 87 Source ↗PDF ↗code ↗Scholar ↗

2023

Gradient Gating for Deep Multi-Rate Learning on Graphs

T. Konstantin Rusch, Benjamin Paul Chamberlain, Michael W. Mahoney, Michael M. Bronstein, Siddhartha Mishra

ICLR 2023poster

We present Gradient Gating (G$^2$), a novel framework for improving the performance of Graph Neural Networks (GNNs). Our framework is based on gating the output of GNN layers with a mechanism for multi-rate flow of message passing information across nodes of the underlying graph. Local gradients are…

Cited by 68 Source ↗PDF ↗code ↗Scholar ↗

2023

Graph Neural Networks for Link Prediction with Subgraph Sketching

Benjamin Paul Chamberlain, Sergey Shirobokov, Emanuele Rossi, Fabrizio Frasca, Thomas Markovich, Nils Yannick Hammerla +2

ICLR 2023top-5%

Many Graph Neural Networks (GNNs) perform poorly compared to simple heuristics on Link Prediction (LP) tasks. This is due to limitations in expressive power such as the inability to count triangles (the backbone of most LP heuristics) and because they can not distinguish automorphic nodes (those hav…

Cited by 133 Source ↗PDF ↗code ↗Scholar ↗

2023

Hyperbolic Deep Reinforcement Learning

Edoardo Cetin, Benjamin Paul Chamberlain, Michael M. Bronstein, Jonathan J Hunt

ICLR 2023top-25%

In deep reinforcement learning (RL), useful information about the state is inherently tied to its possible future successors. Consequently, encoding features that capture the hierarchical relationships between states into the model's latent representations is often conducive to recovering effective…

Cited by 28 Source ↗PDF ↗Scholar ↗

2023

On Over-Squashing in Message Passing Neural Networks: The Impact of Width, Depth, and Topology

Francesco Di Giovanni, Lorenzo Giusti, Federico Barbero, Giulia Luise, Pietro Lio, Michael M. Bronstein

ICML 2023poster

Message Passing Neural Networks (MPNNs) are instances of Graph Neural Networks that leverage the graph to send messages over the edges. This inductive bias leads to a phenomenon known as over-squashing, where a node feature is insensitive to information contained at distant nodes. Despite recent met…

Cited by 158 Source ↗PDF ↗code ↗Scholar ↗

2023

Temporal Graph Benchmark for Machine Learning on Temporal Graphs

Shenyang Huang, Farimah Poursafaei, Jacob Danovitch, Matthias Fey, Weihua Hu, Emanuele Rossi +4

NeurIPS 2023poster

We present the Temporal Graph Benchmark (TGB), a collection of challenging and diverse benchmark datasets for realistic, reproducible, and robust evaluation of machine learning models on temporal graphs. TGB datasets are of large scale, spanning years in duration, incorporate both node and edge-leve…

Cited by 120 Source ↗PDF ↗Scholar ↗

2022

Equivariant Subgraph Aggregation Networks

Beatrice Bevilacqua, Fabrizio Frasca, Derek Lim, Balasubramaniam Srinivasan, Chen Cai, Gopinath Balamurugan +2

ICLR 2022spotlight

Message-passing neural networks (MPNNs) are the leading architecture for deep learning on graph-structured data, in large part due to their simplicity and scalability. Unfortunately, it was shown that these architectures are limited in their expressive power. This paper proposes a novel framework ca…

Cited by 234 Source ↗PDF ↗code ↗Scholar ↗

2022

Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in GNNs

Cristian Bodnar, Francesco Di Giovanni, Benjamin Paul Chamberlain, Pietro Lio, Michael M. Bronstein

NeurIPS 2022accept

Cellular sheaves equip graphs with a ``geometrical'' structure by assigning vector spaces and linear maps to nodes and edges. Graph Neural Networks (GNNs) implicitly assume a graph with a trivial underlying sheaf. This choice is reflected in the structure of the graph Laplacian operator, the propert…

Cited by 213 Source ↗PDF ↗code ↗Scholar ↗

2022

Understanding and Extending Subgraph GNNs by Rethinking Their Symmetries

Fabrizio Frasca, Beatrice Bevilacqua, Michael M. Bronstein, Haggai Maron

NeurIPS 2022accept

Subgraph GNNs are a recent class of expressive Graph Neural Networks (GNNs) which model graphs as collections of subgraphs. So far, the design space of possible Subgraph GNN architectures as well as their basic theoretical properties are still largely unexplored. In this paper, we study the most pro…

Cited by 163 Source ↗PDF ↗code ↗Scholar ↗

2022

Understanding over-squashing and bottlenecks on graphs via curvature

Jake Topping, Francesco Di Giovanni, Benjamin Paul Chamberlain, Xiaowen Dong, Michael M. Bronstein

ICLR 2022oral

Most graph neural networks (GNNs) use the message passing paradigm, in which node features are propagated on the input graph. Recent works pointed to the distortion of information flowing from distant nodes as a factor limiting the efficiency of message passing for tasks relying on long-distance int…

Cited by 584 Source ↗PDF ↗code ↗Scholar ↗

2021

Beltrami Flow and Neural Diffusion on Graphs

Benjamin Paul Chamberlain, James Rowbottom, Davide Eynard, Francesco Di Giovanni, Xiaowen Dong, Michael M. Bronstein

NeurIPS 2021poster

We propose a novel class of graph neural networks based on the discretized Beltrami flow, a non-Euclidean diffusion PDE. In our model, node features are supplemented with positional encodings derived from the graph topology and jointly evolved by the Beltrami flow, producing simultaneously contin…

Cited by 95 Source ↗PDF ↗code ↗Scholar ↗

2021

Fast End-to-End Learning on Protein Surfaces

Freyr Sverrisson, Jean Feydy, Bruno E. Correia, Michael M. Bronstein

CVPR 2021poster

Proteins' biological functions are defined by the geometric and chemical structure of their 3D molecular surfaces. Recent works have shown that geometric deep learning can be used on mesh-based representations of proteins to identify potential functional sites, such as binding targets for potential…

Cited by 189 PDF ↗code ↗Scholar ↗

2021

Partition and Code: learning how to compress graphs

Giorgos Bouritsas, Andreas Loukas, Nikolaos Karalias, Michael M. Bronstein

NeurIPS 2021poster

Can we use machine learning to compress graph data? The absence of ordering in graphs poses a significant challenge to conventional compression algorithms, limiting their attainable gains as well as their ability to discover relevant patterns. On the other hand, most graph compression approaches rel…

Cited by 22 Source ↗PDF ↗code ↗Scholar ↗

2021

Weisfeiler and Lehman Go Cellular: CW Networks

Cristian Bodnar, Fabrizio Frasca, Nina Otter, Yu Guang Wang, Pietro Liò, Guido Montufar +1

NeurIPS 2021poster

Graph Neural Networks (GNNs) are limited in their expressive power, struggle with long-range interactions and lack a principled way to model higher-order structures. These problems can be attributed to the strong coupling between the computational graph and the input graph structure. The recently pr…

Cited by 336 Source ↗PDF ↗code ↗Scholar ↗

2020

Geometrically Principled Connections in Graph Neural Networks

Shunwang Gong, Mehdi Bahri, Michael M. Bronstein, Stefanos Zafeiriou

CVPR 2020poster

Graph convolution operators bring the advantages of deep learning to a variety of graph and mesh processing tasks previously deemed out of reach. With their continued success comes the desire to design more powerful architectures, often by adapting existing deep learning techniques to non-Euclidean…

Cited by 29 PDF ↗Scholar ↗

2020

Weakly-Supervised Mesh-Convolutional Hand Reconstruction in the Wild

Dominik Kulon, Riza Alp Guler, Iasonas Kokkinos, Michael M. Bronstein, Stefanos Zafeiriou

CVPR 2020oral

We introduce a simple and effective network architecture for monocular 3D hand pose estimation consisting of an image encoder followed by a mesh convolutional decoder that is trained through a direct 3D hand mesh reconstruction loss. We train our network by gathering a large-scale dataset of hand ac…

Cited by 247 PDF ↗Scholar ↗

2019

GFrames: Gradient-Based Local Reference Frame for 3D Shape Matching

Simone Melzi, Riccardo Spezialetti, Federico Tombari, Michael M. Bronstein, Luigi Di Stefano, Emanuele Rodola

CVPR 2019oral

We introduce GFrames, a novel local reference frame (LRF) construction for 3D meshes and point clouds. GFrames are based on the computation of the intrinsic gradient of a scalar field defined on top of the input shape. The resulting tangent vector field defines a repeatable tangent direction of the…

Cited by 34 PDF ↗Scholar ↗

2019

Isospectralization, or How to Hear Shape, Style, and Correspondence

Luca Cosmo, Mikhail Panine, Arianna Rampini, Maks Ovsjanikov, Michael M. Bronstein, Emanuele Rodola

CVPR 2019poster

The question whether one can recover the shape of a geometric object from its Laplacian spectrum ('hear the shape of the drum') is a classical problem in spectral geometry with a broad range of implications and applications. While theoretically the answer to this question is negative (there exist ex…

Cited by 65 PDF ↗Scholar ↗

2018

Deep Geometric Matrix Completion: A New Way for Recommender Systems

Federico Monti, Michael M. Bronstein, Xavier Bresson

ICASSP 2018accepted

In the last years, Graph Convolutional Neural Networks gained popularity in the Machine Learning community for their capability of extracting local compositional features on signals defined on non-Euclidean domains. Shape correspondence, document classification, molecular properties predictions are…

Cited by 0 Source ↗Scholar ↗

2017

Geometric Deep Learning on Graphs and Manifolds Using Mixture Model CNNs

Federico Monti, Davide Boscaini, Jonathan Masci, Emanuele Rodola, Jan Svoboda, Michael M. Bronstein

CVPR 2017oral

Deep learning has achieved a remarkable performance breakthrough in several fields, most notably in speech recognition, natural language processing, and computer vision. In particular, convolutional neural network (CNN) architectures currently produce state-of-the-art performance on a variety of ima…

Cited by 2443 PDF ↗Scholar ↗

2016

Efficient Globally Optimal 2D-To-3D Deformable Shape Matching

Zorah Lahner, Emanuele Rodola, Frank R. Schmidt, Michael M. Bronstein, Daniel Cremers

CVPR 2016poster

We propose the first algorithm for non-rigid 2D-to-3D shape matching, where the input is a 2D query shape as well as a 3D target shape and the output is a continuous matching curve represented as a closed contour on the 3D shape. We cast the problem as finding the shortest circular path on the produ…

Cited by 40 PDF ↗Scholar ↗

2015

Functional Correspondence by Matrix Completion

Artiom Kovnatsky, Michael M. Bronstein, Xavier Bresson, Pierre Vandergheynst

CVPR 2015poster

In this paper, we consider the problem of finding dense intrinsic correspondence between manifolds using the recently introduced functional framework. We pose the functional correspondence problem as matrix completion with manifold geometric structure and inducing functional localization with the L1…

Cited by 108 Source ↗PDF ↗Scholar ↗