Publications

Double Gumbel Q-Learning
David Yu-tung Hui
Aaron Courville
Pierre-Luc Bacon
2023-12-11
Neural Information Processing Systems (Accept (spotlight))
doi.org
openreview.net
DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNets
Lazar Atanackovic
Alexander Tong
Bo Wang
Leo J. Lee
Yoshua Bengio
Jason Hartford
One of the grand challenges of cell biology is inferring the gene regulatory network (GRN) which describes interactions between genes and th… (see more)eir products that control gene expression and cellular function. We can treat this as a causal discovery problem but with two non-standard challenges: (1) regulatory networks are inherently cyclic so we should not model a GRN as a directed acyclic graph (DAG), and (2) observations have significant measurement noise, so for typical sample sizes there will always be a large equivalence class of graphs that are likely given the data, and we want methods that capture this uncertainty. Existing methods either focus on challenge (1), identifying cyclic structure from dynamics, or on challenge (2) learning complex Bayesian posteriors over DAGs, but not both. In this paper we leverage the fact that it is possible to estimate the "velocity" of gene expression with RNA velocity techniques to develop an approach that addresses both challenges. Because we have access to velocity information, we can treat the Bayesian structure learning problem as a problem of sparse identification of a dynamical system, capturing cyclic feedback loops through time. Since our objective is to model uncertainty over discrete structures, we leverage Generative Flow Networks (GFlowNets) to estimate the posterior distribution over the combinatorial space of possible sparse dependencies. Our results indicate that our method learns posteriors that better encapsulate the distributions of cyclic structures compared to counterpart state-of-the-art Bayesian structure learning approaches.
2023-12-11
Neural Information Processing Systems (Accept (poster))
doi.org
openreview.net
An Empirical Investigation of the Role of Pre-training in Lifelong Learning
Sanket Vaibhav Mehta
Darshan Patil
Sarath Chandar
Emma Strubell
The lifelong learning paradigm in machine learning is an attractive alternative to the more prominent isolated learning scheme not only due … (see more)to its resemblance to biological learning but also its potential to reduce energy waste by obviating excessive model re-training. A key challenge to this paradigm is the phenomenon of catastrophic forgetting. With the increasing popularity and success of pre-trained models in machine learning, we pose the question: What role does pre-training play in lifelong learning, specifically with respect to catastrophic forgetting? We investigate existing methods in the context of large, pre-trained models and evaluate their performance on a variety of text and image classification tasks, including a large-scale study using a novel data set of 15 diverse NLP tasks. Across all settings, we observe that generic pre-training implicitly alleviates the effects of catastrophic forgetting when learning multiple tasks sequentially compared to randomly initialized models. We then further investigate why pre-training alleviates forgetting in this setting. We study this phenomenon by analyzing the loss landscape, finding that pre-trained weights appear to ease forgetting by leading to wider minima. Based on this insight, we propose jointly optimizing for current task loss and loss basin sharpness to explicitly encourage wider basins during sequential fine-tuning. We show that this optimization approach outperforms several state-of-the-art task-sequential continual learning algorithms across multiple settings, occasionally even without retaining a memory that scales in size with the number of tasks.
2023-12-11
Conference on Neural Information Processing Systems (Accept (Poster))
doi.org
openreview.net
Equivariant Adaptation of Large Pretrained Models
Arnab Kumar Mondal
Siba Smarak Panigrahi
Sékou-Oumar Kaba
Sai Rajeswar
Siamak Ravanbakhsh
Equivariant networks are specifically designed to ensure consistent behavior with respect to a set of input transformations, leading to high… (see more)er sample efficiency and more accurate and robust predictions. However, redesigning each component of prevalent deep neural network architectures to achieve chosen equivariance is a difficult problem and can result in a computationally expensive network during both training and inference. A recently proposed alternative towards equivariance that removes the architectural constraints is to use a simple canonicalization network that transforms the input to a canonical form before feeding it to an unconstrained prediction network. We show here that this approach can effectively be used to make a large pretrained network equivariant. However, we observe that the produced canonical orientations can be misaligned with those of the training distribution, hindering performance. Using dataset-dependent priors to inform the canonicalization function, we are able to make large pretrained models equivariant while maintaining their performance. This significantly improves the robustness of these models to deterministic transformations of the data, such as rotations. We believe this equivariant adaptation of large pretrained models can help their domain-specific applications with known symmetry priors.
2023-12-11
Neural Information Processing Systems (Accept (poster))
doi.org
openreview.net
Feature Likelihood Divergence: Evaluating the Generalization of Generative Models Using Samples
Marco Jiralerspong
Avishek (Joey) Bose
Ian Gemp
Chongli Qin
Yoram Bachrach
Gauthier Gidel
The past few years have seen impressive progress in the development of deep generative models capable of producing high-dimensional, complex… (see more), and photo-realistic data. However, current methods for evaluating such models remain incomplete: standard likelihood-based metrics do not always apply and rarely correlate with perceptual fidelity, while sample-based metrics, such as FID, are insensitive to overfitting, i.e., inability to generalize beyond the training set. To address these limitations, we propose a new metric called the Feature Likelihood Divergence (FLD), a parametric sample-based metric that uses density estimation to provide a comprehensive trichotomic evaluation accounting for novelty (i.e., different from the training samples), fidelity, and diversity of generated samples. We empirically demonstrate the ability of FLD to identify overfitting problem cases, even when previously proposed metrics fail. We also extensively evaluate FLD on various image datasets and model classes, demonstrating its ability to match intuitions of previous metrics like FID while offering a more comprehensive evaluation of generative models. Code is available at https://github.com/marcojira/fld.
2023-12-11
Conference on Neural Information Processing Systems (Accept (poster))
doi.org
openreview.net
For SALE: State-Action Representation Learning for Deep Reinforcement Learning
Scott Fujimoto
Wei-Di Chang
Edward J. Smith
Shixiang Shane Gu
Doina Precup
David Meger
In the field of reinforcement learning (RL), representation learning is a proven tool for complex image-based tasks, but is often overlooked… (see more) for environments with low-level states, such as physical control problems. This paper introduces SALE, a novel approach for learning embeddings that model the nuanced interaction between state and action, enabling effective representation learning from low-level states. We extensively study the design space of these embeddings and highlight important design considerations. We integrate SALE and an adaptation of checkpoints for RL into TD3 to form the TD7 algorithm, which significantly outperforms existing continuous control algorithms. On OpenAI gym benchmark tasks, TD7 has an average performance gain of 276.7% and 50.7% over TD3 at 300k and 5M time steps, respectively, and works in both the online and offline settings.
2023-12-11
Neural Information Processing Systems (Accept (poster))
doi.org
openreview.net
Formalizing locality for normative synaptic plasticity models
Colin Bredenberg
Ezekiel Williams
Cristina Savin
Blake Richards
Guillaume Lajoie
2023-12-11
Neural Information Processing Systems (Accept (poster))
doi.org
openreview.net
GAUCHE: A Library for Gaussian Processes in Chemistry
Ryan-Rhys Griffiths
Leo Klarner
Henry Moss
Aditya Ravuri
Sang Truong
Bojana Rankovic
Samuel Stanton
Yuanqi Du
Arian Jamasb
Gary Tom
Julius Schwartz
Austin Tripp
Aryan Deshwal
Gregory Kell
Anthony Bourached
Alex J. Chan
Jacob Moss
Chengzhi Guo
Simon Frieder
Alpha A. Lee … (see 8 more)
Philippe Schwaller
Jian Tang
Johannes Durholt
Saudamini Chaurasia
Ji Won Park
Felix Strieth-Kalthoff
Bingqing Cheng
Alán Aspuru-Guzik
We introduce GAUCHE, a library for GAUssian processes in CHEmistry. Gaussian processes have long been a cornerstone of probabilistic machine… (see more) learning, affording particular advantages for uncertainty quantification and Bayesian optimisation. Extending Gaussian processes to chemical representations, however, is nontrivial, necessitating kernels defined over structured inputs such as graphs, strings and bit vectors. By defining such kernels in GAUCHE, we seek to open the door to powerful tools for uncertainty quantification and Bayesian optimisation in chemistry. Motivated by scenarios frequently encountered in experimental chemistry, we showcase applications for GAUCHE in molecular discovery and chemical reaction optimisation. The codebase is made available at https://github.com/leojklarner/gauche
2023-12-11
Conference on Neural Information Processing Systems (Accept (poster))
doi.org
openreview.net
GEO-Bench: Toward Foundation Models for Earth Monitoring
Alexandre Lacoste
Nils Lehmann
Pau Rodríguez
Evan David Sherwin
Hannah Kerner
Björn Lütjens
Jeremy Irvin
David Dao
Hamed Alemohammad
Alexandre Drouin
Mehmet Gunturkun
Gabriel Huang
David Vázquez
Dava Newman
Yoshua Bengio
Stefano Ermon
Xiao Xiang Zhu
Recent progress in self-supervision has shown that pre-training large neural networks on vast amounts of unsupervised data can lead to subst… (see more)antial increases in generalization to downstream tasks. Such models, recently coined foundation models, have been transformational to the field of natural language processing. Variants have also been proposed for image data, but their applicability to remote sensing tasks is limited. To stimulate the development of foundation models for Earth monitoring, we propose a benchmark comprised of six classification and six segmentation tasks, which were carefully curated and adapted to be both relevant to the field and well-suited for model evaluation. We accompany this benchmark with a robust methodology for evaluating models and reporting aggregated results to enable a reliable assessment of progress. Finally, we report results for 20 baselines to gain information about the performance of existing models. We believe that this benchmark will be a driver of progress across a variety of Earth monitoring tasks.
2023-12-11
Conference on Neural Information Processing Systems (Accept (Poster))
doi.org
openreview.net
Group Robust Classification Without Any Group Information
Christos Tsirigotis
Joao Monteiro
Pau Rodríguez
David Vázquez
Aaron Courville
Empirical risk minimization (ERM) is sensitive to spurious correlations in the training data, which poses a significant risk when deploying … (see more)systems trained under this paradigm in high-stake applications. While the existing literature focuses on maximizing group-balanced or worst-group accuracy, estimating these accuracies is hindered by costly bias annotations. This study contends that current bias-unsupervised approaches to group robustness continue to rely on group information to achieve optimal performance. Firstly, these methods implicitly assume that all group combinations are represented during training. To illustrate this, we introduce a systematic generalization task on the MPI3D dataset and discover that current algorithms fail to improve the ERM baseline when combinations of observed attribute values are missing. Secondly, bias labels are still crucial for effective model selection, restricting the practicality of these methods in real-world scenarios. To address these limitations, we propose a revised methodology for training and validating debiased models in an entirely bias-unsupervised manner. We achieve this by employing pretrained self-supervised models to reliably extract bias information, which enables the integration of a logit adjustment training loss with our validation criterion. Our empirical analysis on synthetic and real-world tasks provides evidence that our approach overcomes the identified challenges and consistently enhances robust accuracy, attaining performance which is competitive with or outperforms that of state-of-the-art methods, which, conversely, rely on bias labels for validation.
2023-12-11
Conference on Neural Information Processing Systems (Accept (poster))
doi.org
openreview.net
Guiding The Last Layer in Federated Learning with Pre-Trained Models
Gwen Legate
Nicolas Bernier
Lucas Caccia
Edouard Oyallon
Eugene Belilovsky
Federated Learning (FL) is an emerging paradigm that allows a model to be trained across a number of participants without sharing data. Rece… (see more)nt works have begun to consider the effects of using pre-trained models as an initialization point for existing FL algorithms; however, these approaches ignore the vast body of efficient transfer learning literature from the centralized learning setting. Here we revisit the problem of FL from a pre-trained model considered in prior work and expand it to a set of computer vision transfer learning problems. We first observe that simply fitting a linear classification head can be efficient and effective in many cases. We then show that in the FL setting, fitting a classifier using the Nearest Class Means (NCM) can be done exactly and orders of magnitude more efficiently than existing proposals, while obtaining strong performance. Finally, we demonstrate that using a two-phase approach of obtaining the classifier and then fine-tuning the model can yield rapid convergence and improved generalization in the federated setting. We demonstrate the potential our method has to reduce communication and compute costs while achieving better model performance.
2023-12-11
Neural Information Processing Systems (Accept (poster))
doi.org
openreview.net
A Heat Diffusion Perspective on Geodesic Preserving Dimensionality Reduction
Guillaume Huguet
Alexander Tong
Edward De Brouwer
Yanlei Zhang
Guy Wolf
Ian Adelstein
Smita Krishnaswamy
Diffusion-based manifold learning methods have proven useful in representation learning and dimensionality reduction of modern high dimensio… (see more)nal, high throughput, noisy datasets. Such datasets are especially present in fields like biology and physics. While it is thought that these methods preserve underlying manifold structure of data by learning a proxy for geodesic distances, no specific theoretical links have been established. Here, we establish such a link via results in Riemannian geometry explicitly connecting heat diffusion to manifold distances. In this process, we also formulate a more general heat kernel based manifold embedding method that we call heat geodesic embeddings. This novel perspective makes clearer the choices available in manifold learning and denoising. Results show that our method outperforms existing state of the art in preserving ground truth manifold distances, and preserving cluster structure in toy datasets. We also showcase our method on single cell RNA-sequencing datasets with both continuum and cluster structure, where our method enables interpolation of withheld timepoints of data. Finally, we show that parameters of our more general method can be configured to give results similar to PHATE (a state-of-the-art diffusion based manifold learning method) as well as SNE (an attraction/repulsion neighborhood based method that forms the basis of t-SNE).
2023-12-11
Neural Information Processing Systems (Accept (poster))
doi.org
openreview.net