Gal Mishne — accepted AI-conference papers

2026

Coupled Transformer Autoencoder for Disentangling Multi-Region Neural Latent Dynamics

Ram Dyuthi Sristi, Sowmya Manojna Narasimha, Jingya Huang, Alice Despatin, Simon Musall, Vikash Gilja +1

ICLR 2026poster

Simultaneous recordings from thousands of neurons across multiple brain areas reveal rich mixtures of activity that are shared between regions and dynamics that are unique to each region. Existing alignment or multi-view methods neglect temporal structure, whereas dynamical latent-variable models ca…

Cited by 0 Source ↗code ↗Scholar ↗

2026

Multi-Integration of Labels across Categories for Component Identification (MILCCI)

Noga Mudrik, Yuxi Chen, Gal Mishne, Adam Charles

ICML 2026poster

Many fields collect large-scale temporal data through repeated measurements (`trials’), where each trial is labeled with a set of metadata variables spanning several categories. For example, a trial in a neuroscience study may be linked to a value from category (a): task difficulty, and category (b)…

Cited by 0 Source ↗Scholar ↗

2026

Unsupervised Feature Selection Through Group Discovery

Shira Lifshitz, Ofir Lindenbaum, Gal Mishne, Ron Meir, Hadas Benisty

AAAI 2026technical

Unsupervised feature selection (FS) is essential for high-dimensional learning tasks where labels are not available. It helps reduce noise, improve generalization, and enhance interpretability. However, most existing unsupervised FS methods evaluate features in isolation, even though informative sig

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Elucidating Flow Matching ODE Dynamics via Data Geometry and Denoisers

Zhengchao Wan, Qingsong Wang, Gal Mishne, Yusu Wang

ICML 2025poster

Flow matching (FM) models extend ODE sampler based diffusion models into a general framework, significantly reducing sampling steps through learned vector fields. However, the theoretical understanding of FM models, particularly how their sample trajectories interact with underlying data geometry, r…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Joint Hierarchical Representation Learning of Samples and Features via Informed Tree-Wasserstein Distance

Ya-Wei Eileen Lin, Ronald R. Coifman, Gal Mishne, Ronen Talmon

NeurIPS 2025spotlight

High-dimensional data often exhibit hierarchical structures in both modes: samples and features. Yet, most existing approaches for hierarchical representation learning consider only one mode at a time. In this work, we propose an unsupervised method for jointly learning hierarchical representations…

Cited by 0 Source ↗Scholar ↗

2025

RnGCam: High-speed video from rolling & global shutter measurements

Kevin Tandi, Xiang Dai, Chinmay Talegaonkar, Gal Mishne, Nick Antipa

ICCV 2025poster

Compressive video capture encodes a short high-speed video into a single measurement using a low-speed sensor, then computationally reconstructs the original video. Prior implementations rely on expensive hardware and are restricted to imaging sparse scenes with empty backgrounds. We propose RnGCam,…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Tree-Wasserstein Distance for High Dimensional Data with a Latent Feature Hierarchy

Ya-Wei Eileen Lin, Ronald R. Coifman, Gal Mishne, Ronen Talmon

ICLR 2025poster

Finding meaningful distances between high-dimensional data samples is an important scientific task. To this end, we propose a new tree-Wasserstein distance (TWD) for high-dimensional data with two key aspects. First, our TWD is specifically designed for data with a latent feature hierarchy, i.e., th…

Cited by 4 Source ↗PDF ↗Scholar ↗

2024

Comparing Graph Transformers via Positional Encodings

Mitchell Black, Zhengchao Wan, Gal Mishne, Amir Nayyeri, Yusu Wang

ICML 2024poster

The distinguishing power of graph transformers is tied to the choice of *positional encoding*: features used to augment the base transformer with information about the graph. There are two primary types of positional encoding: *absolute positional encodings (APEs)* and *relative positional encodings…

Cited by 13 Source ↗PDF ↗code ↗Scholar ↗

2024

Contextual Feature Selection with Conditional Stochastic Gates

Ram Dyuthi Sristi, Ofir Lindenbaum, Shira Lifshitz, Maria Lavzin, Jackie Schiller, Gal Mishne +1

ICML 2024poster

Feature selection is a crucial tool in machine learning and is widely applied across various scientific disciplines. Traditional supervised methods generally identify a universal set of informative features for the entire population. However, feature relevance often varies with context, while the co…

Cited by 3 Source ↗PDF ↗Scholar ↗

2024

Continuous Partitioning for Graph-Based Semi-Supervised Learning

Chester Holtz, Pengwen Chen, Zhengchao Wan, Chung-Kuan Cheng, Gal Mishne

NeurIPS 2024poster

Laplace learning algorithms for graph-based semi-supervised learning have been shown to produce degenerate predictions at low label rates and in imbalanced class regimes, particularly near class boundaries. We propose CutSSL: a framework for graph-based semi-supervised learning based on continuous n…

Cited by 1 Source ↗PDF ↗Scholar ↗

2024

Learning Cartesian Product Graphs with Laplacian Constraints

Changhao Shi, Gal Mishne

AISTATS 2024poster

Graph Laplacian learning, also known as network topology inference, is a problem of great interest to multiple communities. In Gaussian graphical models (GM), graph learning amounts to endowing covariance selection with the Laplacian structure. In graph signal processing (GSP), it is essential to in…

Cited by 1 Source ↗PDF ↗code ↗Scholar ↗

2024

SiBBlInGS: Similarity-driven Building-Block Inference using Graphs across States

Noga Mudrik, Gal Mishne, Adam Shabti Charles

ICML 2024poster

Time series data across scientific domains are often collected under distinct states (e.g., tasks), wherein latent processes (e.g., biological factors) create complex inter- and intra-state variability. A key approach to capture this complexity is to uncover fundamental interpretable units within th…

Cited by 2 Source ↗PDF ↗code ↗Scholar ↗

2023

Hyperbolic Diffusion Embedding and Distance for Hierarchical Representation Learning

Ya-Wei Eileen Lin, Ronald R. Coifman, Gal Mishne, Ronen Talmon

ICML 2023poster

Finding meaningful representations and distances of hierarchical data is important in many fields. This paper presents a new method for hierarchical data embedding and distance. Our method relies on combining diffusion geometry, a central approach to manifold learning, and hyperbolic geometry. Speci…

Cited by 21 Source ↗PDF ↗code ↗Scholar ↗

2023

Implicit Graphon Neural Representation

Xinyue Xia, Gal Mishne, Yusu Wang

AISTATS 2023poster

Graphons are general and powerful models for generating graphs of varying size. In this paper, we propose to directly model graphons using neural networks, obtaining Implicit Graphon Neural Representation (IGNR). Existing work in modeling and reconstructing graphons often approximates a target graph…

Cited by 10 Source ↗PDF ↗code ↗Scholar ↗

2023

The Numerical Stability of Hyperbolic Representation Learning

Gal Mishne, Zhengchao Wan, Yusu Wang, Sheng Yang

ICML 2023poster

The hyperbolic space is widely used for representing hierarchical datasets due to its ability to embed trees with small distortion. However, this property comes at a price of numerical instability such that training hyperbolic learning models will sometimes lead to catastrophic NaN problems, encount…

Cited by 26 Source ↗PDF ↗code ↗Scholar ↗

2022

DiSC: Differential Spectral Clustering of Features

Ram Dyuthi Sristi, Gal Mishne, Ariel Jaffe

NeurIPS 2022accept

Selecting subsets of features that differentiate between two conditions is a key task in a broad range of scientific domains. In many applications, the features of interest form clusters with similar effects on the data at hand. To recover such clusters we develop DiSC, a data-driven approach for de…

Cited by 6 Source ↗PDF ↗code ↗Scholar ↗

2021

Learning Disentangled Behavior Embeddings

Changhao Shi, Sivan Schwartz, Shahar Levy, Shay Achvat, Maisan Abboud, Amir Ghanayim +2

NeurIPS 2021spotlight

To understand the relationship between behavior and neural activity, experiments in neuroscience often include an animal performing a repeated behavior such as a motor task. Recent progress in computer vision and deep learning has shown great potential in the automated analysis of behavior by levera…

Cited by 17 Source ↗PDF ↗code ↗Scholar ↗

2021

Online Adversarial Purification based on Self-supervised Learning

Changhao Shi, Chester Holtz, Gal Mishne

ICLR 2021poster

Deep neural networks are known to be vulnerable to adversarial examples, where a perturbation in the input space leads to an amplified shift in the latent network representation. In this paper, we combine canonical supervised learning with self-supervised representation learning, and present Self-su…

Cited by 129 Source ↗PDF ↗Scholar ↗

2019

Co-manifold learning with missing data

Gal Mishne, Eric Chi, Ronald Coifman

ICML 2019oral

Representation learning is typically applied to only one mode of a data matrix, either its rows or columns. Yet in many applications, there is an underlying geometry to both the rows and the columns. We propose utilizing this coupled structure to perform co-manifold learning: uncovering the underlyi…

Cited by 19 Source ↗PDF ↗Scholar ↗

2019

Learning Spatially-correlated Temporal Dictionaries for Calcium Imaging

Gal Mishne, Adam S. Charles

ICASSP 2019accepted

Calcium imaging has become a fundamental neural imaging technique, aiming to recover the individual activity of hundreds of neurons in a cortical region. Current methods (mostly matrix factorization) are aimed at detecting neurons in the field-of-view and then inferring the corresponding time-traces…

Cited by 0 Source ↗Scholar ↗

2019

Visualizing the PHATE of Neural Networks

Scott Gigante, Adam S Charles, Smita Krishnaswamy, Gal Mishne

NeurIPS 2019poster

Understanding why and how certain neural networks outperform others is key to guiding future development of network architectures and optimization methods. To this end, we introduce a novel visualization algorithm that reveals the internal geometry of such networks: Multislice PHATE (M-PHATE), the f…

Cited by 36 Source ↗PDF ↗code ↗Scholar ↗

2017

Iterative diffusion-based anomaly detection

Gal Mishne, Israel Cohen

ICASSP 2017accepted

Diffusion maps, when applied to large datasets, are typically constructed by a process of sampling and out-of-sample function extension. However, the performance of anomaly detection in large data when using diffusion maps is sensitive to the chosen samples. In this paper we propose an iterative dat…

Cited by 0 Source ↗Scholar ↗

2016

Improving resolution in supervised patch-based target detection

Ron Amit, Gal Mishne, Ronen Talmon

ICASSP 2016accepted

Recently, a supervised graph-based target detection method was proposed based on a new affinity measure between a set of target training patches and a test image. In this paper, we propose a new high-resolution detection score, which enhances the performance of the previous method by utilizing the k…

Cited by 0 Source ↗Scholar ↗