Publications

Gap Minimization for Knowledge Sharing and Transfer
Boyu Wang
Jorge A. Mendez
Changjian Shui
Fan Zhou
Di Wu
Gezheng Xu
Christian Gagné
Eric R. Eaton
Learning from multiple related tasks by knowledge sharing and transfer has become increasingly relevant over the last two decades. In order … (voir plus)to successfully transfer information from one task to another, it is critical to understand the similarities and differences between the domains. In this paper, we introduce the notion of \emph{performance gap}, an intuitive and novel measure of the distance between learning tasks. Unlike existing measures which are used as tools to bound the difference of expected risks between tasks (e.g.,
2022-12-31
Journal of Machine Learning Research (publié)
arxiv.org
arxiv.org
General Purpose AI Systems in the AI Act: Trying to Fit a Square Peg Into a Round Hole
Claire Boine
David Rolnick
2022-12-31
SSRN Electronic Journal (publié)
doi.org
Generating QM1B with PySCF$_{\text{IPU}}$
Alexander Mathiasen
Hatem Helal
Kerstin Klaser
Paul Balanca
Josef Dean
Carlo Luschi
Dominique Beaini
Andrew William Fitzgibbon
Dominic Masters
2022-12-31
Advances in Neural Information Processing Systems 36 (NeurIPS 2023) (publié)
openreview.net
openreview.net
Generating QM1B with PySCFIPU
Alexander Mathiasen
Hatem Helal
Kerstin Klaser
Paul Balanca
Josef Dean
Carlo Luschi
Dominique Beaini
Andrew William Fitzgibbon
Dominic Masters
2022-12-31
NeurIPS (publié)
doi.org
arxiv.org
Geodesic Sinkhorn for Fast and Accurate Optimal Transport on Manifolds
Guillaume Huguet
Alexander Tong
María Ramos Zapatero
Christopher J. Tape
Guy Wolf
Smita Krishnaswamy
Efficient computation of optimal transport distance between distributions is of growing importance in data science. Sinkhorn-based methods a… (voir plus)re currently the state-of-the-art for such computations, but require
2022-12-31
2023 IEEE 33rd International Workshop on Machine Learning for Signal Processing (MLSP) (publié)
doi.org
arxiv.org
GFlowNets for AI-Driven Scientific Discovery
Moksh Jain
Tristan Deleu
Jason Hartford
Cheng-Hao Liu
Alex Hernandez-Garcia
Yoshua Bengio
Tackling the most pressing problems for humanity, such as the climate crisis and the threat of global pandemics, requires accelerating the p… (voir plus)ace of scientific discovery. While science has traditionally relied on trial and error and even serendipity to a large extent, the last few decades have seen a surge of data-driven scientific discoveries. However, in order to truly leverage large-scale data sets and high-throughput experimental setups, machine learning methods will need to be further improved and better integrated in the scientific discovery pipeline. A key challenge for current machine learning methods in this context is the efficient exploration of very large search spaces, which requires techniques for estimating reducible (epistemic) uncertainty and generating sets of diverse and informative experiments to perform. This motivated a new probabilistic machine learning framework called GFlowNets, which can be applied in the modeling, hypotheses generation and experimental design stages of the experimental science loop. GFlowNets learn to sample from a distribution given indirectly by a reward function corresponding to an unnormalized probability, which enables sampling diverse, high-reward candidates. GFlowNets can also be used to form efficient and amortized Bayesian posterior estimators for causal models conditioned on the already acquired experimental data. Having such posterior models can then provide estimators of epistemic uncertainty and information gain that can drive an experimental design policy. Altogether, here we will argue that GFlowNets can become a valuable tool for AI-driven scientific discovery, especially in scenarios of very large candidate spaces where we have access to cheap but inaccurate measurements or to expensive but accurate measurements. This is a common setting in the context of drug and material discovery, which we use as examples throughout the paper.
2022-12-31
Digital Discovery (publié)
doi.org
arxiv.org
GFlowOut: Dropout with Generative Flow Networks
Dianbo Liu
Moksh Jain
Bonaventure F. P. Dossou
Qianli Shen
Salem Lahlou
Anirudh Goyal
Nikolay Malkin
Chris C. Emezue
Dinghuai Zhang
Nadhir Hassen
Xu Ji
Kenji Kawaguchi
Yoshua Bengio
Bayesian Inference offers principled tools to tackle many critical problems with modern neural networks such as poor calibration and general… (voir plus)ization, and data inefficiency. However, scaling Bayesian inference to large architectures is challenging and requires restrictive approximations. Monte Carlo Dropout has been widely used as a relatively cheap way for approximate Inference and to estimate uncertainty with deep neural networks. Traditionally, the dropout mask is sampled independently from a fixed distribution. Recent works show that the dropout mask can be viewed as a latent variable, which can be inferred with variational inference. These methods face two important challenges: (a) the posterior distribution over masks can be highly multi-modal which can be difficult to approximate with standard variational inference and (b) it is not trivial to fully utilize sample-dependent information and correlation among dropout masks to improve posterior estimation. In this work, we propose GFlowOut to address these issues. GFlowOut leverages the recently proposed probabilistic framework of Generative Flow Networks (GFlowNets) to learn the posterior distribution over dropout masks. We empirically demonstrate that GFlowOut results in predictive distributions that generalize better to out-of-distribution data, and provide uncertainty estimates which lead to better performance in downstream tasks.
2022-12-31
ICML (publié)
doi.org
proceedings.mlr.press
GitHub Copilot AI pair programmer: Asset or Liability?
Arghavan Moradi Dakhel
Vahid Majdinasab
Amin Nikanjam
Foutse Khomh
Michel C. Desmarais
Z. Jiang
Automatic program synthesis is a long-lasting dream in software engineering. Recently, a promising Deep Learning (DL) based solution, called… (voir plus) Copilot, has been proposed by OpenAI and Microsoft as an industrial product. Although some studies evaluate the correctness of Copilot solutions and report its issues, more empirical evaluations are necessary to understand how developers can benefit from it effectively. In this paper, we study the capabilities of Copilot in two different programming tasks: (i) generating (and reproducing) correct and efficient solutions for fundamental algorithmic problems, and (ii) comparing Copilot's proposed solutions with those of human programmers on a set of programming tasks. For the former, we assess the performance and functionality of Copilot in solving selected fundamental problems in computer science, like sorting and implementing data structures. In the latter, a dataset of programming problems with human-provided solutions is used. The results show that Copilot is capable of providing solutions for almost all fundamental algorithmic problems, however, some solutions are buggy and non-reproducible. Moreover, Copilot has some difficulties in combining multiple methods to generate a solution. Comparing Copilot to humans, our results show that the correct ratio of humans' solutions is greater than Copilot's suggestions, while the buggy solutions generated by Copilot require less effort to be repaired.
2022-12-31
J. Syst. Softw. (publié)
doi.org
arxiv.org
GOKU-UI: Ubiquitous Inference through Attention and Multiple Shooting for Continuous-time Generative Models
Germán Abrevaya
Mahta Ramezanian-Panahi
Jean-christophe Gagnon-audet
Irina Rish
Pablo Polosecki
Silvina Ponce Dawson
Guillermo Cecchi
Guillaume Dumas
Scientific Machine Learning (SciML) is a burgeoning field that synergistically combines domain-aware and interpretable models with agnosti… (voir plus)c machine learning techniques. In this work, we introduce GOKU-UI, an evolution of the SciML generative model GOKU-nets. The GOKU-UI broadens the original model’s spectrum to incorporate other classes of differential equations, such as Stochastic Differential Equations (SDEs), and integrates a distributed, i.e. ubiquitous, inference through attention mechanisms and a novel multiple shooting training strategy in the latent space. These enhancements have led to a significant increase in its performance in both reconstruction and forecast tasks, as demonstrated by our evaluation of simulated and empirical data. Specifically, GOKU-UI outperformed all baseline models on synthetic datasets even with a training set 32-fold smaller, underscoring its remarkable data efficiency. Furthermore, when applied to empirical human brain data, while incorporating stochastic Stuart-Landau
2022-12-31
arXiv.org (prépublication)
doi.org
Gradient Masked Averaging for Federated Learning
Irene Tenison
Sai Aravind Sreeramadas
Vaikkunth Mugunthan
Edouard Oyallon
Eugene Belilovsky
Irina Rish
Federated learning (FL) is an emerging paradigm that permits a large number of clients with heterogeneous data to coordinate learning of a u… (voir plus)nified global model without the need to share data amongst each other. A major challenge in federated learning is the heterogeneity of data across client, which can degrade the performance of standard FL algorithms. Standard FL algorithms involve averaging of model parameters or gradient updates to approximate the global model at the server. However, we argue that in heterogeneous settings, averaging can result in information loss and lead to poor generalization due to the bias induced by dominant client gradients. We hypothesize that to generalize better across non-i.i.d datasets, the algorithms should focus on learning the invariant mechanism that is constant while ignoring spurious mechanisms that differ across clients. Inspired from recent works in Out-of-Distribution generalization, we propose a gradient masked averaging approach for FL as an alternative to the standard averaging of client updates. This aggregation technique for client updates can be adapted as a drop-in replacement in most existing federated algorithms. We perform extensive experiments on multiple FL algorithms with in-distribution, real-world, feature-skewed out-of-distribution, and quantity imbalanced datasets and show that it provides consistent improvements, particularly in the case of heterogeneous clients.
2022-12-31
Trans. Mach. Learn. Res. (publié)
openreview.net
openreview.net
Grammar Generative Models for Music Notation
Cheng-Zhi Anna Huang
Deep generative models have been successfully applied in many learning experiments with digital data, such as images or audio. In the field … (voir plus)of music, they can also be used to generate symbolic representations, in the context of problems such as automatic music generation or transcription [1-3]. A significant challenge for generating structured symbolic data in general is obtaining well-formed results. This is especially true in the case of music. It is indeed widely accepted that musical notation represents, well beyond simple sequences of notes, a hierarchical organization of melodic and harmonic information, inducing non-local dependencies between musical objects [4]. A good representation of this information is essential for the interpretation and analysis of music pieces.
2022-12-31
(publié)
www.semanticscholar.org
Graph Inductive Biases in Transformers without Message Passing
Liheng Ma
Chen Lin
Derek Lim
Adriana Romero
Puneet K. Dokania
Mark J. Coates
Philip Torr
Ser-Nam Lim
Transformers for graph data are increasingly widely studied and successful in numerous learning tasks. Graph inductive biases are crucial fo… (voir plus)r Graph Transformers, and previous works incorporate them using message-passing modules and/or positional encodings. However, Graph Transformers that use message-passing inherit known issues of message-passing, and differ significantly from Transformers used in other domains, thus making transfer of research advances more difficult. On the other hand, Graph Transformers without message-passing often perform poorly on smaller datasets, where inductive biases are more crucial. To bridge this gap, we propose the Graph Inductive bias Transformer (GRIT) — a new Graph Transformer that incorporates graph inductive biases without using message passing. GRIT is based on several architectural changes that are each theoretically and empirically justified, including: learned relative positional encodings initialized with random walk probabilities, a flexible attention mechanism that updates node and node-pair representations, and injection of degree information in each layer. We prove that GRIT is expressive — it can express shortest path distances and various graph propagation matrices. GRIT achieves state-of-the-art empirical performance across a variety of graph datasets, thus showing the power that Graph Transformers without message-passing can deliver.
2022-12-31
ICML (publié)
doi.org
proceedings.mlr.press