Emmanuel Bengio

proceedings.mlr.press

Goal-conditioned GFlowNets for Controllable Multi-Objective Molecular Design

Julien Roy

Pierre-Luc Bacon

Christopher Pal

In recent years, in-silico molecular design has received much attention from the machine learning community. When designing a new compound f… (voir plus)or pharmaceutical applications, there are usually multiple properties of such molecules that need to be optimised: binding energy to the target, synthesizability, toxicity, EC50, and so on. While previous approaches have employed a scalarization scheme to turn the multi-objective problem into a preference-conditioned single objective, it has been established that this kind of reduction may produce solutions that tend to slide towards the extreme points of the objective space when presented with a problem that exhibits a concave Pareto front. In this work we experiment with an alternative formulation of goal-conditioned molecular generation to obtain a more controllable conditional model that can uniformly explore solutions along the entire Pareto front.

2023-06-22

ICML.cc/2023/Workshop/DeployableGenerativeAI (accepté)

GFlowNet Foundations

Edward J. Hu

Mo Tiwari

Generative Flow Networks (GFlowNets) have been introduced as a method to sample a diverse set of candidates in an active learning context, w… (voir plus)ith a training objective that makes them approximately sample in proportion to a given reward function. In this paper, we show a number of additional theoretical properties of GFlowNets. They can be used to estimate joint probability distributions and the corresponding marginal distributions where some variables are unspecified and, of particular interest, can represent distributions over composite objects like sets and graphs. GFlowNets amortize the work typically done by computationally expensive MCMC methods in a single but trained generative pass. They could also be used to estimate partition functions and free energies, conditional probabilities of supersets (supergraphs) given a subset (subgraph), as well as marginal distributions over all supersets (supergraphs) of a given set (graph). We introduce variations enabling the estimation of entropy and mutual information, sampling from a Pareto frontier, connections to reward-maximizing policies, and extensions to stochastic environments, continuous actions and modular energy functions.

2022-12-31

Journal of Machine Learning Research (publié)

arxiv.org

Noisy Pairing and Partial Supervision for Stylized Opinion Summarization

Reinald Kim

Mirella Lapata. 2020

Un-611

David M. Krueger

Maxinder S. Kan-620

Somnath Basu

Roy Chowdhury

Chao Zhao

Tanya Goyal

Junyi Jiacheng Xu

Jessy Li

Ivor W. Tsang

James T. Kwok

Neil Houlsby

Andrei Giurgiu

Stanisław Jastrzębski … (voir 22 de plus)

Bruna Morrone

Quentin de Laroussilhe

Mona Gesmundo

Attariyan Sylvain

Gelly

Thomas Wolf

Lysandre Debut

Julien Victor Sanh

Clement Chaumond

Anthony Delangue

Pier-339 Moi

Tim ric Cistac

R´emi Rault

Morgan Louf

Funtow-900 Joe

Sam Davison

Patrick Shleifer

Von Platen

Clara Ma

Yacine Jernite

Julien Plu

Canwen Xu

Opinion summarization research has primar-001 ily focused on generating summaries reflect-002 ing important opinions from customer reviews 0… (voir plus)03 without paying much attention to the writing 004 style. In this paper, we propose the stylized 005 opinion summarization task, which aims to 006 generate a summary of customer reviews in 007 the desired (e.g., professional) writing style. 008 To tackle the difficulty in collecting customer 009 and professional review pairs, we develop a 010 non-parallel training framework, Noisy Pair-011 ing and Partial Supervision ( NAPA ), which 012 trains a stylized opinion summarization sys-013 tem from non-parallel customer and profes-014 sional review sets. We create a benchmark P RO - 015 S UM by collecting customer and professional 016 reviews from Yelp and Michelin. Experimental 017 results on P RO S UM and FewSum demonstrate 018 that our non-parallel training framework con-019 sistently improves both automatic and human 020 evaluations, successfully building a stylized 021 opinion summarization model that can gener-022 ate professionally-written summaries from cus-023 tomer reviews. 024

2022-12-31

(publié)

www.semanticscholar.org

Trajectory balance: Improved credit assignment in GFlowNets

Nikolay Malkin

Moksh Jain

Chen Sun

Yoshua Bengio

Generative flow networks (GFlowNets) are a method for learning a stochastic policy for generating compositional objects, such as graphs or s… (voir plus)trings, from a given unnormalized density by sequences of actions, where many possible action sequences may lead to the same object. We find previously proposed learning objectives for GFlowNets, flow matching and detailed balance, which are analogous to temporal difference learning, to be prone to inefficient credit propagation across long action sequences. We thus propose a new learning objective for GFlowNets, trajectory balance, as a more efficient alternative to previously used objectives. We prove that any global minimizer of the trajectory balance objective can define a policy that samples exactly from the target distribution. In experiments on four distinct domains, we empirically demonstrate the benefits of the trajectory balance objective for GFlowNet convergence, diversity of generated samples, and robustness to long action sequences and large action spaces.

2022-11-28

Neural Information Processing Systems (Accept)

Biological Sequence Design with GFlowNets

Moksh Jain

Alex-Hernandez Garcia

Jarrid Rector-Brooks

Bonaventure F. P. Dossou

Chanakya Ekbote

Michael Kilgour

Payel Das

Design of de novo biological sequences with desired properties, like protein and DNA sequences, often involves an active loop with several r… (voir plus)ounds of molecule ideation and expensive wet-lab evaluations. These experiments can consist of multiple stages, with increasing levels of precision and cost of evaluation, where candidates are filtered. This makes the diversity of proposed candidates a key consideration in the ideation phase. In this work, we propose an active learning algorithm leveraging epistemic uncertainty estimation and the recently proposed GFlowNets as a generator of diverse candidate solutions, with the objective to obtain a diverse batch of useful (as defined by some utility function, for example, the predicted anti-microbial activity of a peptide) and informative candidates after each round. We also propose a scheme to incorporate existing labeled datasets of candidates, in addition to a reward function, to speed up learning in GFlowNets. We present empirical results on several biological sequence design tasks, and we find that our method generates more diverse and novel batches with high scoring candidates compared to existing approaches.

2022-07-18

International Conference on Machine Learning (Accept for Short Presentation)

proceedings.mlr.press

E VALUATING G ENERALIZATION IN GF LOW N ETS FOR M OLECULE D ESIGN

Moksh J. Jain

Cheng-Hao Liu

Michael M. Bronstein

Deep learning bears promise for drug discovery problems such as de novo molecular design. Generating data to train such models is a costly a… (voir plus)nd time-consuming process, given the need for wet-lab experiments or expensive simulations. This problem is compounded by the notorious data-hungriness of machine learning algorithms. In small molecule generation the recently proposed GFlowNet method has shown good performance in generating diverse high-scoring candidates, and has the interesting advantage of being an off-policy offline method. Finding an appropriate generalization evaluation metric for such models, one predictive of the desired search performance (i.e. finding high-scoring diverse candidates), will help guide online data collection for such an algorithm. In this work, we develop techniques for evaluating GFlowNet performance on a test set, and identify the most promising metric for predicting generalization. We present empirical results on several small-molecule design tasks in drug discovery, for several GFlowNet training setups, and we find a metric strongly correlated with diverse high-scoring batch generation. This metric should be used to identify the best generative model from which to sample batches of molecules to be evaluated.

2022-04-04

ICLR.cc/2022/Workshop/MLDD (poster)

Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation

This paper is about the problem of learning a stochastic policy for generating an object (like a molecular graph) from a sequence of actions… (voir plus), such that the probability of generating an object is proportional to a given positive reward for that object. Whereas standard return maximization tends to converge to a single return-maximizing sequence, there are cases where we would like to sample a diverse set of high-return solutions. These arise, for example, in black-box function optimization when few rounds are possible, each with large batches of queries, where the batches should be diverse, e.g., in the design of new molecules. One can also see this as a problem of approximately converting an energy function to a generative distribution. While MCMC methods can achieve that, they are expensive and generally only perform local exploration. Instead, training a generative policy amortizes the cost of search during training and yields to fast generation. Using insights from Temporal Difference learning, we propose GFlowNet, based on a view of the generative process as a flow network, making it possible to handle the tricky case where different trajectories can yield the same final state, e.g., there are many ways to sequentially add atoms to generate some molecular graph. We cast the set of trajectories as a flow and convert the flow consistency equations into a learning objective, akin to the casting of the Bellman equations into Temporal Difference methods. We prove that any global minimum of the proposed objectives yields a policy which samples from the desired distribution, and demonstrate the improved performance and diversity of GFlowNet on a simple domain where there are many modes to the reward function, and on a molecule synthesis task.

2021-12-06

Conference on Neural Information Processing Systems (Accept (Poster))

TDprop: Does Adaptive Optimization With Jacobi Preconditioning Help Temporal Difference Learning?

We investigate whether Jacobi preconditioning, accounting for the bootstrap term in temporal difference (TD) learning, can help boost perfor… (voir plus)mance of adaptive optimizers. Our method, TDprop, computes a per-parameter learning rate based on the diagonal preconditioning of the TD update rule. We show how this can be used in both n-step returns and TD(λ). Our theoretical findings demonstrate that including this additional preconditioning information is comparable to normal semi-gradient TD if the optimal learning rate is found for both via a hyperparameter search. This matches our experimental results. In Deep RL experiments using Expected SARSA, TDprop meets or exceeds the performance of Adam in all tested games under near-optimal learning rates, but a well-tuned SGD can yield similar performance in most settings. Our findings suggest that Jacobi preconditioning may improve upon Adam in Deep RL, but despite incorporating additional information from the TD bootstrap term, may not always be better than SGD. Moreover, they suggest that more theoretical investigations are needed to understand adaptive optimizers under optimal hyperparameter regimes in TD learning: simpler methods may, surprisingly, be theoretically comparable after a hyperparameter search.

2021-05-02

Adaptive Agents and Multi-Agent Systems (publié)

Correcting Momentum in Temporal Difference Learning

Joelle Pineau

Doina Precup

A common optimization tool used in deep reinforcement learning is momentum, which consists in accumulating and discounting past gradients, r… (voir plus)eapplying them at each iteration. We argue that, unlike in supervised learning, momentum in Temporal Difference (TD) learning accumulates gradients that become doubly stale: not only does the gradient of the loss change due to parameter updates, the loss itself changes due to bootstrapping. We first show that this phenomenon exists, and then propose a first-order correction term to momentum. We show that this correction term improves sample efficiency in policy evaluation by correcting target value drift. An important insight of this work is that deep RL methods are not always best served by directly importing techniques from the supervised setting.

2020-12-31

arXiv (prépublication)

Interference and Generalization in Temporal Difference Learning

Joelle Pineau

Doina Precup

We study the link between generalization and interference in temporal-difference (TD) learning. Interference is defined as the inner product… (voir plus) of two different gradients, representing their alignment. This quantity emerges as being of interest from a variety of observations about neural networks, parameter sharing and the dynamics of learning. We find that TD easily leads to low-interference, under-generalizing parameters, while the effect seems reversed in supervised learning. We hypothesize that the cause can be traced back to the interplay between the dynamics of interference and bootstrapping. This is supported empirically by several observations: the negative relationship between the generalization gap and interference in TD, the negative effect of bootstrapping on interference and the local coherence of targets, and the contrast between the propagation rate of information in TD(0) versus TD(

2020-11-20

Proceedings of the 37th International Conference on Machine Learning (publié)

proceedings.mlr.press

TDprop: Does Jacobi Preconditioning Help Temporal Difference Learning?

We investigate whether Jacobi preconditioning, accounting for the bootstrap term in temporal difference (TD) learning, can help boost perfor… (voir plus)mance of adaptive optimizers. Our method, TDprop, computes a per parameter learning rate based on the diagonal preconditioning of the TD update rule. We show how this can be used in both

2019-12-31

arXiv (prépublication)