AIConfPaper
← Search

Marc Brockschmidt

19 accepted papers

2023

Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamics

Leon Klein, Andrew Y. K. Foong, Tor Erlend Fjelde, Bruno Kacper Mlodozeniec, Marc Brockschmidt, Sebastian Nowozin +2
NeurIPS 2023spotlight

*Molecular dynamics* (MD) simulation is a widely used technique to simulate molecular systems, most commonly at the all-atom resolution where equations of motion are integrated with timesteps on the order of femtoseconds ($1\textrm{fs}=10^{-15}\textrm{s}$). MD is often used to compute equilibrium p…

Cited by 46Source ↗PDF ↗code ↗Scholar ↗
2022

Learning to Complete Code with Sketches

Daya Guo, Alexey Svyatkovskiy, Jian Yin, Nan Duan, Marc Brockschmidt, Miltiadis Allamanis
ICLR 2022poster

Code completion is usually cast as a language modelling problem, i.e., continuing an input in a left-to-right fashion. However, in practice, some parts of the completion (e.g., string literals) may be very hard to predict, whereas subsequent parts directly follow from the context. To handle this, we…

Cited by 55Source ↗PDF ↗Scholar ↗
2022

Learning to Extend Molecular Scaffolds with Structural Motifs

Krzysztof Maziarz, Henry Richard Jackson-Flux, Pashmina Cameron, Finton Sirockin, Nadine Schneider, Nikolaus Stiefl +2
ICLR 2022poster

Recent advancements in deep learning-based modeling of molecules promise to accelerate in silico drug discovery. A plethora of generative models is available, building molecules either atom-by-atom and bond-by-bond or fragment-by-fragment. However, many drug discovery projects require a fixed scaffo…

Cited by 106Source ↗PDF ↗code ↗Scholar ↗
2021

Copy That! Editing Sequences by Copying Spans

Sheena Panthaplackel, Miltiadis Allamanis, Marc Brockschmidt
AAAI 2021technical

Neural sequence-to-sequence models are finding increasing use in editing of documents, for example in correcting a text document or repairing source code. In this paper, we argue that common seq2seq models (with a facility to copy single tokens) are not a natural fit for such tasks, as they have to…

Cited by 28Source ↗PDF ↗code ↗Scholar ↗
2021

FS-Mol: A Few-Shot Learning Dataset of Molecules

Megan Stanley, John F Bronskill, Krzysztof Maziarz, Hubert Misztela, Jessica Lanini, Marwin Segler +2
NeurIPS 2021poster

Small datasets are ubiquitous in drug discovery as data generation is expensive and can be restricted for ethical reasons (e.g. in vivo experiments). A widely applied technique in early drug discovery to identify novel active molecules against a protein target is modelling quantitative structure-act…

Cited by 95Source ↗Scholar ↗
2021

Self-Supervised Bug Detection and Repair

Miltiadis Allamanis, Henry Richard Jackson-Flux, Marc Brockschmidt
NeurIPS 2021poster

Machine learning-based program analyses have recently shown the promise of integrating formal and probabilistic reasoning towards aiding software development. However, in the absence of large annotated corpora, training these analyses is challenging. Towards addressing this, we present BugLab, an ap…

Cited by 135Source ↗PDF ↗code ↗Scholar ↗
2019

Generative Code Modeling with Graphs

Marc Brockschmidt, Miltiadis Allamanis, Alexander L. Gaunt, Oleksandr Polozov
ICLR 2019poster

Generative models forsource code are an interesting structured prediction problem, requiring to reason about both hard syntactic and semantic constraints as well as about natural, likely programs. We present a novel model for this problem that uses a graph to represent the intermediate state of the…

Cited by 227Source ↗PDF ↗code ↗Scholar ↗
2019

Learning to Represent Edits

Pengcheng Yin, Graham Neubig, Miltiadis Allamanis, Marc Brockschmidt, Alexander L. Gaunt
ICLR 2019poster

We introduce the problem of learning distributed representations of edits. By combining a "neural editor" with an "edit encoder", our models learn to represent the salient information of an edit and can be used to apply edits to new inputs. We experiment on natural language and source code edit data…

Cited by 133Source ↗PDF ↗code ↗Scholar ↗
2019

Program Synthesis and Semantic Parsing with Learned Code Idioms

Eui Chul Shin, Miltiadis Allamanis, Marc Brockschmidt, Alex Polozov
NeurIPS 2019poster

Program synthesis of general-purpose source code from natural language specifications is challenging due to the need to reason about high-level patterns in the target program and low-level implementation details at the same time. In this work, we present Patois, a system that allows a neural program…

Cited by 101Source ↗PDF ↗code ↗Scholar ↗
2018

Constrained Graph Variational Autoencoders for Molecule Design

Qi Liu, Miltiadis Allamanis, Marc Brockschmidt, Alexander Gaunt
NeurIPS 2018poster

Graphs are ubiquitous data structures for representing interactions between entities. With an emphasis on applications in chemistry, we explore the task of learning to generate graphs that conform to a distribution observed in training data. We propose a variational autoencoder model in which both e…

Cited by 617Source ↗PDF ↗code ↗Scholar ↗
2018

Graph Partition Neural Networks for Semi-Supervised Classification

Renjie Liao, Marc Brockschmidt, Daniel Tarlow, Alexander Gaunt, Raquel Urtasun, Richard S. Zemel
ICLR 2018workshop

We present graph partition neural networks (GPNN), an extension of graph neural networks (GNNs) able to handle extremely large graphs. GPNNs alternate between locally propagating information between nodes in small subgraphs and globally propagating information between the subgraphs. To efficiently p…

Cited by 91Source ↗code ↗Scholar ↗
2017

DeepCoder: Learning to Write Programs

Matej Balog, Alexander L. Gaunt, Marc Brockschmidt, Sebastian Nowozin, Daniel Tarlow
ICLR 2017poster

We develop a first line of attack for solving programming competition-style problems from input-output examples using deep learning. The approach is to train a neural network to predict properties of the program that generated the outputs from the inputs. We use the neural network's predictions to a…

Cited by 752Source ↗Scholar ↗
2017

Differentiable Programs with Neural Libraries

Alexander L. Gaunt, Marc Brockschmidt, Nate Kushman, Daniel Tarlow
ICML 2017poster

We develop a framework for combining differentiable programming languages with neural networks. Using this framework we create end-to-end trainable systems that learn to write interpretable algorithms with perceptual components. We explore the benefits of inductive biases for strong generalization a…

Cited by 75Source ↗PDF ↗Scholar ↗