Search Results for author: Sungsoo Ahn

Found 46 papers, 21 papers with code

Chain-of-Thoughts for Molecular Understanding

no code implementations8 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.

MOFFlow: Flow Matching for Structure Prediction of Metal-Organic Frameworks

no code implementations7 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.

Generative Flows on Synthetic Pathway for Drug Design

1 code implementation6 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.

Drug Discovery

Can LLMs Generate Diverse Molecules? Towards Alignment with Structural Diversity

no code implementations4 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.

Diversity Drug Discovery

REBIND: Enhancing ground-state molecular conformation via force-based graph rewiring

no code implementations4 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.

Atomic Forces Computational chemistry

Adaptive teachers for amortized samplers

no code implementations2 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.

Decision Making Efficient Exploration +1

Improving Robustness to Multiple Spurious Correlations by Multi-Objective Optimization

no code implementations5 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.

Iterated Energy-based Flow Matching for Sampling from Boltzmann Densities

no code implementations29 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.

Transition Path Sampling with Improved Off-Policy Training of Diffusion Path Samplers

1 code implementation30 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.

Drug Discovery

Pessimistic Backward Policy for GFlowNets

1 code implementation25 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.

Diversity

Tackling Prevalent Conditions in Unsupervised Combinatorial Optimization: Cardinality, Minimum, Covering, and More

2 code implementations14 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.

Combinatorial Optimization

Gaussian Plane-Wave Neural Operator for Electron Density Estimation

2 code implementations5 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.

Density Estimation

Hybrid Neural Representations for Spherical Data

no code implementations5 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.

Super-Resolution

Triplet Edge Attention for Algorithmic Reasoning

no code implementations9 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.

Graph Attention Graph Neural Network +1

A Simple and Scalable Representation for Graph Generation

1 code implementation4 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.

Graph Generation Molecular Graph Generation

Non-backtracking Graph Neural Networks

1 code implementation11 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.

Graph Neural Network Node Classification +1

Learning Energy Decompositions for Partial Inference of GFlowNets

no code implementations5 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.

Local Search GFlowNets

2 code implementations4 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.

Bootstrapped Training of Score-Conditioned Generator for Offline Design of Biological Sequences

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.

EPIC: Graph Augmentation with Edit Path Interpolation via Learnable Cost

no code implementations2 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.

Data Augmentation Graph Classification

Graph Generation with $K^2$-trees

1 code implementation30 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.

Drug Discovery Graph Generation

Imitating Graph-Based Planning with Goal-Conditioned Policies

1 code implementation20 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.

Reinforcement Learning (RL)

A Closer Look at the Intervention Procedure of Concept Bottleneck Models

1 code implementation28 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.

Fairness

Diffusion Probabilistic Models for Structured Node Classification

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.

Classification Node Classification

Substructure-Atom Cross Attention for Molecular Representation Learning

no code implementations15 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.

Drug Discovery Graph Neural Network +4

Learning Debiased Classifier with Biased Committee

1 code implementation22 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.

Attribute

RoMA: Robust Model Adaptation for Offline Model-based Optimization

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.

Spanning Tree-based Graph Generation for Molecules

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.

Graph Generation Molecular Graph Generation

What Makes Better Augmentation Strategies? Augment Difficult but Not too Different

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.

Data Augmentation Semantic Similarity +3

Abstract Reasoning via Logic-guided Generation

no code implementations22 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.

Self-Improved Retrosynthetic Planning

1 code implementation9 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.

Multi-step retrosynthesis valid

RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning

no code implementations3 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.

Contrastive Learning Retrosynthesis

Layer-adaptive sparsity for the Magnitude-based Pruning

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.

Image Classification Network Pruning

Learning from Failure: Training Debiased Classifier from Biased Classifier

2 code implementations6 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.

Action Recognition Facial Attribute Classification +1

Guiding Deep Molecular Optimization with Genetic Exploration

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.

Imitation Learning

Learning What to Defer for Maximum Independent Sets

1 code implementation ICML 2020 Sungsoo Ahn, Younggyo Seo, Jinwoo Shin

Designing efficient algorithms for combinatorial optimization appears ubiquitously in various scientific fields.

Combinatorial Optimization

Deep Auto-Deferring Policy for Combinatorial Optimization

no code implementations25 Sep 2019 Sungsoo Ahn, Younggyo Seo, Jinwoo Shin

Designing efficient algorithms for combinatorial optimization appears ubiquitously in various scientific fields.

Combinatorial Optimization Computational Efficiency

Variational Information Distillation for Knowledge Transfer

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.

Knowledge Distillation Transfer Learning

Gauged Mini-Bucket Elimination for Approximate Inference

no code implementations5 Jan 2018 Sungsoo Ahn, Michael Chertkov, Jinwoo Shin, Adrian Weller

Recently, so-called gauge transformations were used to improve variational lower bounds on $Z$.

Gauging Variational Inference

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).

Variational Inference

MCMC assisted by Belief Propagation

no code implementations29 May 2016 Sungsoo Ahn, Michael Chertkov, Jinwoo Shin

Furthermore, we also design an efficient rejection-free MCMC scheme for approximating the full series.

Minimum Weight Perfect Matching via Blossom Belief Propagation

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).

Combinatorial Optimization

Cannot find the paper you are looking for? You can Submit a new open access paper.