Emmanuel Bengio

Glen Berseth

Nikolay Malkin

Jarrid Rector-Brooks

This paper presents a practical application of Relative Trajectory Balance (RTB), a recently introduced off-policy reinforcement learning (R… (see more)L) objective that can asymptotically solve Bayesian inverse problems optimally. We extend the original work by using RTB to train conditional diffusion model posteriors from pretrained unconditional priors for challenging linear and non-linear inverse problems in vision, and science. We use the objective alongside techniques such as off-policy backtracking exploration to improve training. Importantly, our results show that existing training-free diffusion posterior methods struggle to perform effective posterior inference in latent space due to inherent biases.

2025-03-06

ICLR.cc/2025/Workshop/DeLTa (poster)

Action abstractions for amortized sampling

Oussama Boussif

Lena Nehale Ezzine

Joseph D Viviano

Michał Koziarski

Moksh J. Jain

Nikolay Malkin

Rim Assouel

2025-01-22

ICLR.cc/2025/Conference (poster)

Adaptive teachers for amortized samplers

Minsu Kim

Sanghyeok Choi

Taeyoung Yun

Leo Feng

Jarrid Rector-Brooks

Sungsoo Ahn

Jinkyoo Park

Nikolay Malkin

Amortized inference is the task of training a parametric model, such as a neural network, to approximate a distribution with a given unnorma… (see more)lized density where exact sampling is intractable. When sampling is implemented as a sequential decision-making process, reinforcement learning (RL) methods, such as generative flow networks, can be used to train the sampling policy. Off-policy RL training facilitates the discovery of diverse, high-reward candidates, but existing methods still face challenges in efficient exploration. We propose to use an adaptive training distribution (the Teacher) to guide the training of the primary amortized sampler (the Student) by prioritizing high-loss regions. The Teacher, an auxiliary behavior model, is trained to sample high-error regions of the Student and can generalize across unexplored modes, thereby enhancing mode coverage by providing an efficient training curriculum. We validate the effectiveness of this approach in a synthetic environment designed to present an exploration challenge, two diffusion-based sampling tasks, and four biochemical discovery tasks demonstrating its ability to improve sample efficiency and mode coverage.

2025-01-22

ICLR.cc/2025/Conference (poster)

Towards Improving Exploration through Sibling Augmented GFlowNets

Kanika Madan

Alex Lamb

Glen Berseth

Exploration is a key factor for the success of an active learning agent, especially when dealing with sparse extrinsic terminal rewards and … (see more)long trajectories. We introduce Sibling Augmented Generative Flow Networks (SA-GFN), a novel framework designed to enhance exploration and training efficiency of Generative Flow Networks (GFlowNets). SA-GFN uses a decoupled dual network architecture, comprising of a main Behavior Network and an exploratory Sibling Network, to enable a diverse exploration of the underlying distribution using intrinsic rewards. Inspired by the ideas on exploration from reinforcement learning, SA-GFN provides a general-purpose exploration and learning paradigm that integrates with multiple GFlowNet training objectives and is especially helpful for exploration over a wide range of sparse or low reward distributions and task structures. An extensive set of experiments across a diverse range of tasks, reward structures and trajectory lengths, along with a thorough set of ablations, demonstrate the superior performance of SA-GFN in terms of exploration efficacy and convergence speed as compared to the existing methods. In addition, SA-GFN's versatility and compatibility with different GFlowNet training objectives and intrinsic reward methods underscores its broad applicability in various problem domains.

2025-01-22

ICLR.cc/2025/Conference (poster)

Efficient Biological Data Acquisition through Inference Set Design

Ihor Neporozhnii

Julien Roy

Jason Hartford

In drug discovery, highly automated high-throughput laboratories are used to screen a large number of compounds in search of effective drugs… (see more). These experiments are expensive, so one might hope to reduce their cost by only experimenting on a subset of the compounds, and predicting the outcomes of the remaining experiments. In this work, we model this scenario as a sequential subset selection problem: we aim to select the smallest set of candidates in order to achieve some desired level of accuracy for the system as a whole. Our key observation is that, if there is heterogeneity in the difficulty of the prediction problem across the input space, selectively obtaining the labels for the hardest examples in the acquisition pool will leave only the relatively easy examples to remain in the inference set, leading to better overall system performance. We call this mechanism inference set design, and propose the use of a confidence-based active learning solution to prune out these challenging examples. Our algorithm includes an explicit stopping criterion that interrupts the acquisition loop when it is sufficiently confident that the system has reached the target performance. Our empirical studies on image and molecular datasets, as well as a real-world large-scale biological assay, show that active learning for inference set design leads to significant reduction in experimental cost while retaining high system performance.

2024-10-25

ArXiv (preprint)

Efficient Biological Data Acquisition through Inference Set Design

Ihor Neporozhnii

Julien Roy

Jason Hartford

In drug discovery, highly automated high-throughput laboratories are used to screen a large number of compounds in search of effective drugs… (see more). These experiments are expensive, so one might hope to reduce their cost by only experimenting on a subset of the compounds, and predicting the outcomes of the remaining experiments. In this work, we model this scenario as a sequential subset selection problem: we aim to select the smallest set of candidates in order to achieve some desired level of accuracy for the system as a whole. Our key observation is that, if there is heterogeneity in the difficulty of the prediction problem across the input space, selectively obtaining the labels for the hardest examples in the acquisition pool will leave only the relatively easy examples to remain in the inference set, leading to better overall system performance. We call this mechanism inference set design, and propose the use of a confidence-based active learning solution to prune out these challenging examples. Our algorithm includes an explicit stopping criterion that interrupts the acquisition loop when it is sufficiently confident that the system has reached the target performance. Our empirical studies on image and molecular datasets, as well as a real-world large-scale biological assay, show that active learning for inference set design leads to significant reduction in experimental cost while retaining high system performance.

2024-10-25

ArXiv (preprint)

Improved Off-policy Reinforcement Learning in Biological Sequence Design

Hyeonah Kim

Minsu Kim

Taeyoung Yun

Sanghyeok Choi

Alex Hern'andez-Garc'ia

Jinkyoo Park

Designing biological sequences with desired properties is a significant challenge due to the combinatorially vast search space and the high … (see more)cost of evaluating each candidate sequence. To address these challenges, reinforcement learning (RL) methods, such as GFlowNets, utilize proxy models for rapid reward evaluation and annotated data for policy training. Although these approaches have shown promise in generating diverse and novel sequences, the limited training data relative to the vast search space often leads to the misspecification of proxy for out-of-distribution inputs. We introduce

2024-10-06

ArXiv (preprint)

Improved Off-policy Reinforcement Learning in Biological Sequence Design

Hyeonah Kim

Minsu Kim

Taeyoung Yun

Sanghyeok Choi

Alex Hern'andez-Garc'ia

Jinkyoo Park

Designing biological sequences with desired properties is a significant challenge due to the combinatorially vast search space and the high … (see more)cost of evaluating each candidate sequence. To address these challenges, reinforcement learning (RL) methods, such as GFlowNets, utilize proxy models for rapid reward evaluation and annotated data for policy training. Although these approaches have shown promise in generating diverse and novel sequences, the limited training data relative to the vast search space often leads to the misspecification of proxy for out-of-distribution inputs. We introduce

2024-10-06

ArXiv (preprint)

Amortizing intractable inference in diffusion models for vision, language, and control

Siddarth Venkatraman

Moksh J. Jain

Luca Scimeca

Minsu Kim

Marcin Sendera

Mohsin Hasan

Luke Rowe

Sarthak Mittal

Pablo Lemos

Alexandre Adam

Jarrid Rector-Brooks

Glen Berseth

Nikolay Malkin

Diffusion models have emerged as effective distribution estimators in vision, language, and reinforcement learning, but their use as priors … (see more)in downstream tasks poses an intractable posterior inference problem. This paper studies amortized sampling of the posterior over data,

2024-09-25

NeurIPS.cc/2024/Conference (poster)

QGFN: Controllable Greediness with Action Values

Elaine Lau

Stephen Zhewen Lu

Ling Pan

Doina Precup

Generative Flow Networks (GFlowNets; GFNs) are a family of energy-based generative methods for combinatorial objects, capable of generating … (see more)diverse and high-utility samples. However, consistently biasing GFNs towards producing high-utility samples is non-trivial. In this work, we leverage connections between GFNs and reinforcement learning (RL) and propose to combine the GFN policy with an action-value estimate,

2024-09-25

NeurIPS.cc/2024/Conference (poster)

GFlowNet Pretraining with Inexpensive Rewards

Mohit Pandey

Gopeshh Subbaraj

Generative Flow Networks (GFlowNets), a class of generative models have recently emerged as a suitable framework for generating diverse and … (see more)high-quality molecular structures by learning from unnormalized reward distributions. Previous works in this direction often restrict exploration by using predefined molecular fragments as building blocks, limiting the chemical space that can be accessed. In this work, we introduce Atomic GFlowNets (A-GFNs), a foundational generative model leveraging individual atoms as building blocks to explore drug-like chemical space more comprehensively. We propose an unsupervised pre-training approach using offline drug-like molecule datasets, which conditions A-GFNs on inexpensive yet informative molecular descriptors such as drug-likeliness, topological polar surface area, and synthetic accessibility scores. These properties serve as proxy rewards, guiding A-GFNs towards regions of chemical space that exhibit desirable pharmacological properties. We further our method by implementing a goal-conditioned fine-tuning process, which adapts A-GFNs to optimize for specific target properties. In this work, we pretrain A-GFN on the ZINC15 offline dataset and employ robust evaluation metrics to show the effectiveness of our approach when compared to other relevant baseline methods in drug design.

2024-09-15

ArXiv (preprint)

GFlowNet Pretraining with Inexpensive Rewards

Mohit Pandey

Gopeshh Subbaraj

Generative Flow Networks (GFlowNets), a class of generative models have recently emerged as a suitable framework for generating diverse and … (see more)high-quality molecular structures by learning from unnormalized reward distributions. Previous works in this direction often restrict exploration by using predefined molecular fragments as building blocks, limiting the chemical space that can be accessed. In this work, we introduce Atomic GFlowNets (A-GFNs), a foundational generative model leveraging individual atoms as building blocks to explore drug-like chemical space more comprehensively. We propose an unsupervised pre-training approach using offline drug-like molecule datasets, which conditions A-GFNs on inexpensive yet informative molecular descriptors such as drug-likeliness, topological polar surface area, and synthetic accessibility scores. These properties serve as proxy rewards, guiding A-GFNs towards regions of chemical space that exhibit desirable pharmacological properties. We further our method by implementing a goal-conditioned fine-tuning process, which adapts A-GFNs to optimize for specific target properties. In this work, we pretrain A-GFN on the ZINC15 offline dataset and employ robust evaluation metrics to show the effectiveness of our approach when compared to other relevant baseline methods in drug design.

2024-09-15

ArXiv (preprint)