Author name cluster

Wei Wang 0010

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

7 papers

1 author row

ICML Conference 2025 Conference Paper

GIVE: Structured Reasoning of Large Language Models with Knowledge Graph Inspired Veracity Extrapolation

Jiashu He
Mingyu Derek Ma
Jinxuan Fan
Dan Roth 0001
Wei Wang 0010
Alejandro Ribeiro

Existing approaches based on context prompting or reinforcement learning (RL) to improve the reasoning capacities of large language models (LLMs) depend on the LLMs’ internal knowledge to produce reliable Chain-Of-Thought (CoT). However, no matter the size of LLMs, certain problems cannot be resolved in a single forward pass. Meanwhile, agent-based reasoning systems require access to a comprehensive nonparametric knowledge base, which is often costly or not feasible for use in scientific and niche domains. We present Graph Inspired Veracity Extrapolation (GIVE), a novel reasoning method that merges parametric and non-parametric memories to improve accurate reasoning with minimal external input. GIVE guides the LLM agent to select the most pertinent expert data ($\textbf{observe}$), engage in query-specific associative thinking ($\textbf{reflect}$), and then synthesize this information to produce the final output ($\textbf{speak}$). Extensive experiments demonstrated the following benefits of our framework: (1) GIVE increases the performance of LLMs across various sizes. (2) In some scenarios, GIVE allows smaller LLMs to surpass larger, more sophisticated ones in scientific tasks ($\textbf{GPT3. 5T + GIVE > GPT4}$). (3) GIVE is effective on scientific and open-domain assessments. (4) GIVE is a training-free method that enables LLMs to tackle new problems that extend beyond their training data (up to $\textbf{43. 5}$% $\rightarrow$ $\textbf{88. 2}$% accuracy improvement). (5) GIVE allows LLM agents to reason using both restricted (very small) and noisy (very large) knowledge sources, accommodating knowledge graphs (KG) ranging from $\textbf{135}$ to more than $\textbf{840k}$ nodes. (6) The reasoning process involved in GIVE is fully interpretable. Our code is available at https: //github. com/Jason-Tree/GIVE

Details

ICLR Conference 2025 Conference Paper

Mixture of In-Context Prompters for Tabular PFNs

Derek Qiang Xu
F. Olcay Cirit
Reza Asadi
Yizhou Sun
Wei Wang 0010

Recent benchmarks find In-Context Learning (ICL) outperforms both deep learning and tree-based algorithms on small tabular datasets. However, on larger datasets, ICL for tabular learning suffers in both efficiency and effectiveness. In terms of efficiency, transformers incur linear space and quadratic time complexity w.r.t. context size. In terms of effectiveness, contexts at inference encounter distribution shift compared to contexts from pretraining. We propose MixturePFN, which extends Sparse Mixture of Experts to the state-of-the-art ICL for tabular learning model. Specifically, MixturePFN finetunes a specialized ICL expert on each cluster of tabular data and routes new test samples to appropriate experts at inference. MixturePFN supports constant-size contexts by splitting large training datasets into more manageable clusters. MixturePFN addresses distribution shift by finetuning an expert on each training dataset cluster via bootstrapping. Extensive experimental results shows MixturePFN outperforms 19 baselines both in mean rank and as the Condorcet winner across 36 diverse tabular datasets under both accuracy and F1 score with statistical significance.

Details

ICML Conference 2025 Conference Paper

Rethink GraphODE Generalization within Coupled Dynamical System

Guancheng Wan
Zijie Huang 0002
Wanjia Zhao
Xiao Luo 0001
Yizhou Sun
Wei Wang 0010

Coupled dynamical systems govern essential phenomena across physics, biology, and engineering, where components interact through complex dependencies. While Graph Ordinary Differential Equations (GraphODE) offer a powerful framework to model these systems, their generalization capabilities degrade severely under limited observational training data due to two fundamental flaws: (i) the entanglement of static attributes and dynamic states in the initialization process, and (ii) the reliance on context-specific coupling patterns during training, which hinders performance in unseen scenarios. In this paper, we propose a Generalizable GraphODE with disentanglement and regularization (GREAT) to address these challenges. Through systematic analysis via the Structural Causal Model, we identify backdoor paths that undermine generalization and design two key modules to mitigate their effects. The Dynamic-Static Equilibrium Decoupler (DyStaED) disentangles static and dynamic states via orthogonal subspace projections, ensuring robust initialization. Furthermore, the Causal Mediation for Coupled Dynamics (CMCD) employs variational inference to estimate latent causal factors, reducing spurious correlations and enhancing universal coupling dynamics. Extensive experiments across diverse dynamical systems demonstrate that ours outperforms state-of-the-art methods within both in-distribution and out-of-distribution.

Details

ICLR Conference 2024 Conference Paper

Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks

Yanqiao Zhu 0001
Jeehyun Hwang
Keir Adams
Zhen Liu 0069
Bozhao Nan
Brock Stenfors
Yuanqi Du
Jatin Chauhan

Molecular Representation Learning (MRL) has proven impactful in numerous biochemical applications such as drug discovery and enzyme design. While Graph Neural Networks (GNNs) are effective at learning molecular representations from a 2D molecular graph or a single 3D structure, existing works often overlook the flexible nature of molecules, which continuously interconvert across conformations via chemical bond rotations and minor vibrational perturbations. To better account for molecular flexibility, some recent works formulate MRL as an ensemble learning problem, focusing on explicitly learning from a set of conformer structures. However, most of these studies have limited datasets, tasks, and models. In this work, we introduce the first MoleculAR Conformer Ensemble Learning (MARCEL) benchmark to thoroughly evaluate the potential of learning on con- former ensembles and suggest promising research directions. MARCEL includes four datasets covering diverse molecule- and reaction-level properties of chemically diverse molecules including organocatalysts and transition-metal catalysts, extending beyond the scope of common GNN benchmarks that are confined to drug-like molecules. In addition, we conduct a comprehensive empirical study, which benchmarks representative 1D, 2D, and 3D MRL models, along with two strategies that explicitly incorporate conformer ensembles into 3D models. Our findings reveal that direct learning from an accessible conformer space can improve performance on a variety of tasks and models.

Details

ICML Conference 2024 Conference Paper

SciBench: Evaluating College-Level Scientific Problem-Solving Abilities of Large Language Models

Xiaoxuan Wang
Ziniu Hu
Pan Lu
Yanqiao Zhu 0001
Jieyu Zhang 0001
Satyen Subramaniam
Arjun R. Loomba
Shichang Zhang

Most existing Large Language Model (LLM) benchmarks on scientific problem reasoning focus on problems grounded in high-school subjects and are confined to elementary algebraic operations. To systematically examine the reasoning capabilities required for solving complex scientific problems, we introduce an expansive benchmark suite SciBench for LLMs. SciBench contains a carefully curated dataset featuring a range of collegiate-level scientific problems from mathematics, chemistry, and physics domains. Based on the dataset, we conduct an in-depth benchmarking study of representative open-source and proprietary LLMs with various prompting strategies. The results reveal that current LLMs fall short of delivering satisfactory performance, with the best overall score of merely 43. 22%. Furthermore, through a detailed user study, we categorize the errors made by LLMs into ten problem-solving abilities. Our analysis indicates that no single prompting strategy significantly outperforms the others and some strategies that demonstrate improvements in certain problem-solving skills could result in declines in other skills. We envision that SciBench will catalyze further developments in the reasoning abilities of LLMs, thereby ultimately contributing to scientific research and discovery.

Details

ICML Conference 2021 Conference Paper

GLSearch: Maximum Common Subgraph Detection via Learning to Search

Yunsheng Bai
Derek Xu
Yizhou Sun
Wei Wang 0010

Detecting the Maximum Common Subgraph (MCS) between two input graphs is fundamental for applications in drug synthesis, malware detection, cloud computing, etc. However, MCS computation is NP-hard, and state-of-the-art MCS solvers rely on heuristic search algorithms which in practice cannot find good solution for large graph pairs given a limited computation budget. We propose GLSearch, a Graph Neural Network (GNN) based learning to search model. Our model is built upon the branch and bound algorithm, which selects one pair of nodes from the two input graphs to expand at a time. We propose a novel GNN-based Deep Q-Network (DQN) to select the node pair, making the search process much faster. Experiments on synthetic and real-world graph pairs demonstrate that our model learns a search strategy that is able to detect significantly larger common subgraphs than existing MCS solvers given the same computation budget. GLSearch can be potentially extended to solve many other combinatorial problems with constraints on graphs.

Details

ICML Conference 2020 Conference Paper

Robust Graph Representation Learning via Neural Sparsification

Cheng Zheng 0004
Bo Zong
Wei Cheng 0002
Dongjin Song
Jingchao Ni
Wenchao Yu
Haifeng Chen
Wei Wang 0010

Graph representation learning serves as the core of important prediction tasks, ranging from product recommendation to fraud detection. Real-life graphs usually have complex information in the local neighborhood, where each node is described by a rich set of features and connects to dozens or even hundreds of neighbors. Despite the success of neighborhood aggregation in graph neural networks, task-irrelevant information is mixed into nodes’ neighborhood, making learned models suffer from sub-optimal generalization performance. In this paper, we present NeuralSparse, a supervised graph sparsification technique that improves generalization power by learning to remove potentially task-irrelevant edges from input graphs. Our method takes both structural and non-structural information as input, utilizes deep neural networks to parameterize sparsification processes, and optimizes the parameters by feedback signals from downstream tasks. Under the NeuralSparse framework, supervised graph sparsification could seamlessly connect with existing graph neural networks for more robust performance. Experimental results on both benchmark and private datasets show that NeuralSparse can yield up to 7. 2% improvement in testing accuracy when working with existing graph neural networks on node classification tasks.

Details