Taeyoung YUN

Zixuan Liu

Can Chen

2025-03-21

ArXiv (preprint)

Offline Model-Based Optimization: Comprehensive Review

Minsu Kim

Jiayao Gu

Ye Yuan

Zixuan Liu

Can Chen

2025-03-21

ArXiv (preprint)

Adaptive teachers for amortized samplers

Minsu Kim

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)

Improved Off-policy Reinforcement Learning in Biological Sequence Design

Minsu Kim

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

Minsu Kim

Alex Hernandez-Garcia

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)

Learning to Scale Logits for Temperature-Conditional GFlowNets

Minsu Kim

Joohwan Ko

Dinghuai Zhang

Ling Pan

Woo Chang Kim

Jinkyoo Park

Emmanuel Bengio

GFlowNets are probabilistic models that sequentially generate compositional structures through a stochastic policy. Among GFlowNets, tempera… (see more)ture-conditional GFlowNets can introduce temperature-based controllability for exploration and exploitation. We propose \textit{Logit-scaling GFlowNets} (Logit-GFN), a novel architectural design that greatly accelerates the training of temperature-conditional GFlowNets. It is based on the idea that previously proposed approaches introduced numerical challenges in the deep network training, since different temperatures may give rise to very different gradient profiles as well as magnitudes of the policy's logits. We find that the challenge is greatly reduced if a learned function of the temperature is used to scale the policy's logits directly. Also, using Logit-GFN, GFlowNets can be improved by having better generalization capabilities in offline learning and mode discovery capabilities in online learning, which is empirically verified in various biological and chemical tasks. Our code is available at https://github.com/dbsxodud-11/logit-gfn

2024-05-01

ICML.cc/2024/Conference (poster)

Local Search GFlowNets

Minsu Kim

Sungsoo Ahn

Jinkyoo Park

Generative Flow Networks (GFlowNets) are amortized sampling methods that learn a distribution over discrete objects proportional to their re… (see more)wards. GFlowNets exhibit a remarkable ability to generate diverse samples, yet occasionally struggle to consistently produce samples with high rewards due to over-exploration on wide sample space. This paper proposes to train GFlowNets with local search, which focuses on exploiting high-rewarded sample space to resolve this issue. Our main idea is to explore the local neighborhood via backtracking and reconstruction guided by backward and forward policies, respectively. This allows biasing the samples toward high-reward solutions, which is not possible for a typical GFlowNet solution generation scheme, which uses the forward policy to generate the solution from scratch. Extensive experiments demonstrate a remarkable performance improvement in several biochemical tasks. Source code is available: https://github.com/dbsxodud-11/ls_gfn.

2024-01-16

ICLR.cc/2024/Conference (spotlight)

Local Search GFlowNets.

Minsu Kim

Sungsoo Ahn

Jinkyoo Park

2024-01-01

ICLR (published)

dblp.uni-trier.de

Learning to Scale Logits for Temperature-Conditional GFlowNets

Minsu Kim

Joohwan Ko

Dinghuai Zhang

Ling Pan

Woo Chang Kim

Jinkyoo Park

GFlowNets are probabilistic models that learn a stochastic policy that sequentially generates compositional structures, such as molecular gr… (see more)aphs. They are trained with the objective of sampling such objects with probability proportional to the object's reward. Among GFlowNets, the temperature-conditional GFlowNets represent a family of policies indexed by temperature, and each is associated with the correspondingly tempered reward function. The major benefit of temperature-conditional GFlowNets is the controllability of GFlowNets' exploration and exploitation through adjusting temperature. We propose a \textit{Learning to Scale Logits for temperature-conditional GFlowNets} (LSL-GFN), a novel architectural design that greatly accelerates the training of temperature-conditional GFlowNets. It is based on the idea that previously proposed temperature-conditioning approaches introduced numerical challenges in the training of the deep network because different temperatures may give rise to very different gradient profiles and ideal scales of the policy's logits. We find that the challenge is greatly reduced if a learned function of the temperature is used to scale the policy's logits directly. We empirically show that our strategy dramatically improves the performances of GFlowNets, outperforming other baselines, including reinforcement learning and sampling methods, in terms of discovering diverse modes in multiple biochemical tasks.

2023-10-27

NeurIPS.cc/2023/Workshop/AI4Science (poster)

Local Search GFlowNets

Minsu Kim

Sungsoo Ahn

Jinkyoo Park

2023-10-04

ArXiv (preprint)

Local Search GFlowNets

Minsu Kim

Sungsoo Ahn

Jinkyoo Park

Generative Flow Networks (GFlowNets) are amortized sampling methods that learn a distribution over discrete objects proportional to their re… (see more)wards. GFlowNets exhibit a remarkable ability to generate diverse samples, yet occasionally struggle to consistently produce samples with high rewards due to over-exploration on wide sample space. This paper proposes to train GFlowNets with local search, which focuses on exploiting high-rewarded sample space to resolve this issue. Our main idea is to explore the local neighborhood via backtracking and reconstruction guided by backward and forward policies, respectively. This allows biasing the samples toward high-reward solutions, which is not possible for a typical GFlowNet solution generation scheme, which uses the forward policy to generate the solution from scratch. Extensive experiments demonstrate a remarkable performance improvement in several biochemical tasks. Source code is available: https://github.com/dbsxodud-11/ls_gfn.

2023-10-04

ArXiv (preprint)

Local Search GFlowNets

Minsu Kim

Sungsoo Ahn

Jinkyoo Park

Generative Flow Networks (GFlowNets) are amortized sampling methods that learn a distribution over discrete objects proportional to their re… (see more)wards. GFlowNets exhibit a remarkable ability to generate diverse samples, yet occasionally struggle to consistently produce samples with high rewards due to over-exploration on wide sample space. This paper proposes to train GFlowNets with local search, which focuses on exploiting high-rewarded sample space to resolve this issue. Our main idea is to explore the local neighborhood via backtracking and reconstruction guided by backward and forward policies, respectively. This allows biasing the samples toward high-reward solutions, which is not possible for a typical GFlowNet solution generation scheme, which uses the forward policy to generate the solution from scratch. Extensive experiments demonstrate a remarkable performance improvement in several biochemical tasks. Source code is available: https://github.com/dbsxodud-11/ls_gfn.

2023-10-04

ArXiv (preprint)