Search Results for author:
Found 33 papers, 14 papers with code
Variational Information Distillation for Knowledge Transfer
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.
Learning from Failure: Training Debiased Classifier from Biased Classifier
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
Layer-adaptive sparsity for the Magnitude-based Pruning
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.
Learning What to Defer for Maximum Independent Sets
Designing efficient algorithms for combinatorial optimization appears ubiquitously in various scientific fields.
Guiding Deep Molecular Optimization with Genetic Exploration
De novo molecular design attempts to search over the chemical space for molecules with the desired property.
Self-Improved Retrosynthetic Planning
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
A Closer Look at the Intervention Procedure of Concept Bottleneck Models
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.
Imitating Graph-Based Planning with Goal-Conditioned Policies
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.
Learning Debiased Classifier with Biased Committee
We propose a new method for training debiased classifiers with no spurious attribute label.
Local Search GFlowNets
Generative Flow Networks (GFlowNets) are amortized sampling methods that learn a distribution over discrete objects proportional to their rewards.
A Simple and Scalable Representation for Graph Generation
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.
Bootstrapped Training of Score-Conditioned Generator for Offline Design of Biological Sequences
The subsequent stage involves bootstrapping, which augments the training dataset with self-generated data labeled by a proxy score function.
Graph Generation with $K^2$-trees
Generating graphs from a target distribution is a significant challenge across many domains, including drug discovery and social network analysis.
Gaussian Plane-Wave Neural Operator for Electron Density Estimation
This work studies machine learning for electron density prediction, which is fundamental for understanding chemical systems and density functional theory (DFT) simulations.
Bucket Renormalization for Approximate Inference
Probabilistic graphical models are a key tool in machine learning applications.
Gauged Mini-Bucket Elimination for Approximate Inference
Recently, so-called gauge transformations were used to improve variational lower bounds on $Z$.
Gauging Variational Inference
Computing partition function is the most important statistical inference task arising in applications of Graphical Models (GM).
MCMC assisted by Belief Propagation
Furthermore, we also design an efficient rejection-free MCMC scheme for approximating the full series.
Minimum Weight Perfect Matching via Blossom Belief Propagation
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).
RetCL: A Selection-based Approach for Retrosynthesis via Contrastive Learning
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.
Abstract Reasoning via Logic-guided Generation
Abstract reasoning, i. e., inferring complicated patterns from given observations, is a central building block of artificial general intelligence.
What Makes Better Augmentation Strategies? Augment Difficult but Not too Different
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.
Spanning Tree-based Graph Generation for Molecules
In this paper, we explore the problem of generating molecules using deep neural networks, which has recently gained much interest in chemistry.
RoMA: Robust Model Adaptation for Offline Model-based Optimization
We consider the problem of searching an input maximizing a black-box objective function given a static dataset of input-output queries.
Deep Auto-Deferring Policy for Combinatorial Optimization
Designing efficient algorithms for combinatorial optimization appears ubiquitously in various scientific fields.
Substructure-Atom Cross Attention for Molecular Representation Learning
Designing a neural network architecture for molecular representation is crucial for AI-driven drug discovery and molecule design.
EPIC: Graph Augmentation with Edit Path Interpolation via Learnable Cost
Graph-based models have become increasingly important in various domains, but the limited size and diversity of existing graph datasets often limit their performance.
Symmetric Replay Training: Enhancing Sample Efficiency in Deep Reinforcement Learning for Combinatorial Optimization
Deep reinforcement learning (DRL) has significantly advanced the field of combinatorial optimization (CO).
Learning Energy Decompositions for Partial Inference of GFlowNets
In particular, we focus on improving GFlowNet with partial inference: training flow functions with the evaluation of the intermediate states or transitions.
Non-backtracking Graph Neural Networks
In this work, we propose to resolve such a redundancy via the non-backtracking graph neural network (NBA-GNN) that updates a message without incorporating the message from the previously visited node.
Triplet Edge Attention for Algorithmic Reasoning
In this work, we introduce a new graph neural network layer called Triplet Edge Attention (TEA), an edge-aware graph attention layer.
Diffusion Probabilistic Models for Structured Node Classification
This paper studies structured node classification on graphs, where the predictions should consider dependencies between the node labels.
Hybrid Neural Representations for Spherical Data
In this paper, we study hybrid neural representations for spherical data, a domain of increasing relevance in scientific research.
