no code implementations • 8 Oct 2024 • Yunhui Jang, Jaehyung Kim, Sungsoo Ahn
The adaptation of large language models (LLMs) to chemistry has shown promising performance in molecular understanding tasks, such as generating a text description from a molecule.
no code implementations • 7 Oct 2024 • Nayoung Kim, Seongsu Kim, Minsu Kim, Jinkyoo Park, Sungsoo Ahn
Metal-organic frameworks (MOFs) are a class of crystalline materials with promising applications in many areas such as carbon capture and drug delivery.
1 code implementation • 6 Oct 2024 • Seonghwan Seo, Minsu Kim, Tony Shen, Martin Ester, Jinkyoo Park, Sungsoo Ahn, Woo Youn Kim
This enables RxnFlow to learn generative flows over extensive action spaces comprising combinations of 1. 2 million building blocks and 71 reaction templates without significant computational overhead.
no code implementations • 4 Oct 2024 • Hyosoon Jang, Yunhui Jang, Jaehyung Kim, Sungsoo Ahn
In response, we propose a new method for fine-tuning molecular generative LLMs to autoregressively generate a set of structurally diverse molecules, where each molecule is generated by conditioning on the previously generated molecules.
no code implementations • 4 Oct 2024 • Taewon Kim, Hyunjin Seo, Sungsoo Ahn, Eunho Yang
Predicting the ground-state 3D molecular conformations from 2D molecular graphs is critical in computational chemistry due to its profound impact on molecular properties.
no code implementations • 2 Oct 2024 • Minsu Kim, Sanghyeok Choi, Taeyoung Yun, Emmanuel Bengio, Leo Feng, Jarrid Rector-Brooks, Sungsoo Ahn, Jinkyoo Park, Nikolay Malkin, Yoshua Bengio
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.
no code implementations • 5 Sep 2024 • Nayeong Kim, Juwon Kang, Sungsoo Ahn, Jungseul Ok, Suha Kwak
We study the problem of training an unbiased and accurate model given a dataset with multiple biases.
no code implementations • 29 Aug 2024 • Dongyeop Woo, Sungsoo Ahn
In this work, we consider the problem of training a generator from evaluations of energy functions or unnormalized densities.
1 code implementation • 30 May 2024 • Kiyoung Seong, Seonghyun Park, SeongHwan Kim, Woo Youn Kim, Sungsoo Ahn
In this paper, we introduce a novel approach that trains diffusion path samplers (DPS) for transition path sampling (TPS) without the need for CVs.
1 code implementation • 25 May 2024 • Hyosoon Jang, Yunhui Jang, Minsu Kim, Jinkyoo Park, Sungsoo Ahn
This paper studies Generative Flow Networks (GFlowNets), which learn to sample objects proportionally to a given reward function through the trajectory of state transitions.
2 code implementations • 14 May 2024 • Fanchen Bu, Hyeonsoo Jo, Soo Yong Lee, Sungsoo Ahn, Kijung Shin
Then, for various conditions commonly involved in different CO problems, we derive nontrivial objectives and derandomization to meet the targets.
no code implementations • 8 Feb 2024 • Nayoung Kim, Minsu Kim, Sungsoo Ahn, Jinkyoo Park
Antibody design plays a pivotal role in advancing therapeutics.
2 code implementations • 5 Feb 2024 • Seongsu Kim, Sungsoo Ahn
This work studies machine learning for electron density prediction, which is fundamental for understanding chemical systems and density functional theory (DFT) simulations.
no code implementations • 5 Feb 2024 • Hyomin Kim, Yunhui Jang, Jaeho Lee, Sungsoo Ahn
In this paper, we study hybrid neural representations for spherical data, a domain of increasing relevance in scientific research.
no code implementations • 9 Dec 2023 • YeonJoon Jung, Sungsoo Ahn
In this work, we introduce a new graph neural network layer called Triplet Edge Attention (TEA), an edge-aware graph attention layer.
1 code implementation • 4 Dec 2023 • Yunhui Jang, Seul Lee, Sungsoo Ahn
Recently, there has been a surge of interest in employing neural networks for graph generation, a fundamental statistical learning problem with critical applications like molecule design and community analysis.
1 code implementation • 11 Oct 2023 • Seonghyun Park, Narae Ryu, Gahee Kim, Dongyeop Woo, Se-Young Yun, Sungsoo Ahn
In this work, we propose to resolve such a redundancy issue via the non-backtracking graph neural network (NBA-GNN) that updates a message without incorporating the message from the previously visited node.
no code implementations • 5 Oct 2023 • Hyosoon Jang, Minsu Kim, Sungsoo Ahn
In particular, we focus on improving GFlowNet with partial inference: training flow functions with the evaluation of the intermediate states or transitions.
2 code implementations • 4 Oct 2023 • Minsu Kim, Taeyoung Yun, Emmanuel Bengio, Dinghuai Zhang, Yoshua Bengio, Sungsoo Ahn, Jinkyoo Park
Generative Flow Networks (GFlowNets) are amortized sampling methods that learn a distribution over discrete objects proportional to their rewards.
3 code implementations • 29 Jun 2023 • Federico Berto, Chuanbo Hua, Junyoung Park, Laurin Luttmann, Yining Ma, Fanchen Bu, Jiarui Wang, Haoran Ye, Minsu Kim, Sanghyeok Choi, Nayeli Gast Zepeda, André Hottung, Jianan Zhou, Jieyi Bi, Yu Hu, Fei Liu, Hyeonah Kim, Jiwoo Son, Haeyeon Kim, Davide Angioni, Wouter Kool, Zhiguang Cao, Qingfu Zhang, Joungho Kim, Jie Zhang, Kijung Shin, Cathy Wu, Sungsoo Ahn, Guojie Song, Changhyun Kwon, Kevin Tierney, Lin Xie, Jinkyoo Park
To fill this gap, we introduce RL4CO, a unified and extensive benchmark with in-depth library coverage of 23 state-of-the-art methods and more than 20 CO problems.
1 code implementation • NeurIPS 2023 • Minsu Kim, Federico Berto, Sungsoo Ahn, Jinkyoo Park
The subsequent stage involves bootstrapping, which augments the training dataset with self-generated data labeled by a proxy score function.
no code implementations • 2 Jun 2023 • Jaeseung Heo, Seungbeom Lee, Sungsoo Ahn, Dongwoo Kim
Data augmentation plays a critical role in improving model performance across various domains, but it becomes challenging with graph data due to their complex and irregular structure.
1 code implementation • 2 Jun 2023 • Hyeonah Kim, Minsu Kim, Sungsoo Ahn, Jinkyoo Park
Deep reinforcement learning (DRL) has significantly advanced the field of combinatorial optimization (CO).
1 code implementation • 30 May 2023 • Yunhui Jang, Dongwoo Kim, Sungsoo Ahn
Generating graphs from a target distribution is a significant challenge across many domains, including drug discovery and social network analysis.
1 code implementation • 20 Mar 2023 • Junsu Kim, Younggyo Seo, Sungsoo Ahn, Kyunghwan Son, Jinwoo Shin
Recently, graph-based planning algorithms have gained much attention to solve goal-conditioned reinforcement learning (RL) tasks: they provide a sequence of subgoals to reach the target-goal, and the agents learn to execute subgoal-conditioned policies.
1 code implementation • 28 Feb 2023 • Sungbin Shin, Yohan Jo, Sungsoo Ahn, Namhoon Lee
Concept bottleneck models (CBMs) are a class of interpretable neural network models that predict the target response of a given input based on its high-level concepts.
no code implementations • NeurIPS 2023 • Hyosoon Jang, Seonghyun Park, Sangwoo Mo, Sungsoo Ahn
This paper studies structured node classification on graphs, where the predictions should consider dependencies between the node labels.
no code implementations • 15 Oct 2022 • Jiye Kim, Seungbeom Lee, Dongwoo Kim, Sungsoo Ahn, Jaesik Park
Designing a neural network architecture for molecular representation is crucial for AI-driven drug discovery and molecule design.
1 code implementation • 22 Jun 2022 • Nayeong Kim, Sehyun Hwang, Sungsoo Ahn, Jaesik Park, Suha Kwak
We propose a new method for training debiased classifiers with no spurious attribute label.
no code implementations • NeurIPS 2021 • Sihyun Yu, Sungsoo Ahn, Le Song, Jinwoo Shin
We consider the problem of searching an input maximizing a black-box objective function given a static dataset of input-output queries.
no code implementations • ICLR 2022 • Sungsoo Ahn, Binghong Chen, Tianzhe Wang, Le Song
In this paper, we explore the problem of generating molecules using deep neural networks, which has recently gained much interest in chemistry.
no code implementations • ICLR 2022 • Jaehyung Kim, Dongyeop Kang, Sungsoo Ahn, Jinwoo Shin
Remarkably, our method is more effective on the challenging low-data and class-imbalanced regimes, and the learned augmentation policy is well-transferable to the different tasks and models.
no code implementations • 22 Jul 2021 • Sihyun Yu, Sangwoo Mo, Sungsoo Ahn, Jinwoo Shin
Abstract reasoning, i. e., inferring complicated patterns from given observations, is a central building block of artificial general intelligence.
1 code implementation • 9 Jun 2021 • Junsu Kim, Sungsoo Ahn, Hankook Lee, Jinwoo Shin
Our main idea is based on a self-improving procedure that trains the model to imitate successful trajectories found by itself.
Ranked #4 on Multi-step retrosynthesis on USPTO-190
no code implementations • 3 May 2021 • Hankook Lee, Sungsoo Ahn, Seung-Woo Seo, You Young Song, Eunho Yang, Sung-Ju Hwang, Jinwoo Shin
Retrosynthesis, of which the goal is to find a set of reactants for synthesizing a target product, is an emerging research area of deep learning.
1 code implementation • ICLR 2021 • Jaeho Lee, Sejun Park, Sangwoo Mo, Sungsoo Ahn, Jinwoo Shin
Recent discoveries on neural network pruning reveal that, with a carefully chosen layerwise sparsity, a simple magnitude-based pruning achieves state-of-the-art tradeoff between sparsity and performance.
2 code implementations • 6 Jul 2020 • Junhyun Nam, Hyuntak Cha, Sungsoo Ahn, Jaeho Lee, Jinwoo Shin
Neural networks often learn to make predictions that overly rely on spurious correlation existing in the dataset, which causes the model to be biased.
Ranked #1 on Out-of-Distribution Generalization on ImageNet-W
2 code implementations • NeurIPS 2020 • Sungsoo Ahn, Junsu Kim, Hankook Lee, Jinwoo Shin
De novo molecular design attempts to search over the chemical space for molecules with the desired property.
1 code implementation • ICML 2020 • Sungsoo Ahn, Younggyo Seo, Jinwoo Shin
Designing efficient algorithms for combinatorial optimization appears ubiquitously in various scientific fields.
no code implementations • 25 Sep 2019 • Sungsoo Ahn, Younggyo Seo, Jinwoo Shin
Designing efficient algorithms for combinatorial optimization appears ubiquitously in various scientific fields.
2 code implementations • CVPR 2019 • Sungsoo Ahn, Shell Xu Hu, Andreas Damianou, Neil D. Lawrence, Zhenwen Dai
We further demonstrate the strength of our method on knowledge transfer across heterogeneous network architectures by transferring knowledge from a convolutional neural network (CNN) to a multi-layer perceptron (MLP) on CIFAR-10.
no code implementations • ICML 2018 • Sungsoo Ahn, Michael Chertkov, Adrian Weller, Jinwoo Shin
Probabilistic graphical models are a key tool in machine learning applications.
no code implementations • 5 Jan 2018 • Sungsoo Ahn, Michael Chertkov, Jinwoo Shin, Adrian Weller
Recently, so-called gauge transformations were used to improve variational lower bounds on $Z$.
no code implementations • NeurIPS 2017 • Sungsoo Ahn, Michael Chertkov, Jinwoo Shin
Computing partition function is the most important statistical inference task arising in applications of Graphical Models (GM).
no code implementations • 29 May 2016 • Sungsoo Ahn, Michael Chertkov, Jinwoo Shin
Furthermore, we also design an efficient rejection-free MCMC scheme for approximating the full series.
no code implementations • NeurIPS 2015 • Sungsoo Ahn, Sejun Park, Michael Chertkov, Jinwoo Shin
Max-product Belief Propagation (BP) is a popular message-passing algorithm for computing a Maximum-A-Posteriori (MAP) assignment over a distribution represented by a Graphical Model (GM).