271 citations · 596 across the 31 of their papers we have counts for
25 papers · 1 filter
Resolving Action Bottleneck: Agentic Reinforcement Learning Informed by Token-Level Energy
Langzhou He, Junyou Zhu, Yue Zhou +7
Agentic reinforcement learning trains large language models using multi-turn trajectories that interleave long reasoning traces with short environment-facing actions. Common policy…
PAINET: A Principled Efficient Transformer for 3D Dynamics Modeling
Kai Yang, Yuqi Huang, Junheng Tao +2
Modeling 3D dynamics is a fundamental problem in multi-body systems across scientific and engineering domains and has important practical implications in object trajectory predicti…
SGFormer: Single-Layer Graph Transformers with Approximation-Free Linear Complexity
Qitian Wu, Kai Yang, Hengrui Zhang +2
Learning representations on large graphs is a long-standing challenge due to the inter-dependence nature. Transformers recently have shown promising performance on small graphs tha…
Transformers from Diffusion: A Unified Framework for Neural Message Passing
Qitian Wu, David Wipf, Junchi Yan
Learning representations for structured data with certain geometries (e.g., observed or unobserved) is a fundamental challenge, wherein message passing neural networks (MPNNs) have…
GeoMix: Towards Geometry-Aware Data Augmentation
Wentao Zhao, Qitian Wu, Chenxiao Yang +1
Mixup has shown considerable success in mitigating the challenges posed by limited labeled data in image classification. By synthesizing samples through the interpolation of featur…
Learning Divergence Fields for Shift-Robust Graph Representations
Qitian Wu, Fan Nie, Chenxiao Yang +1
Real-world data generation often involves certain geometries (e.g., graphs) that induce instance-level interdependence. This characteristic makes the generalization of learning mod…
DiffPuter: Empowering Diffusion Models for Missing Data Imputation
Hengrui Zhang, Liancheng Fang, Qitian Wu +1
Generative models play an important role in missing data imputation in that they aim to learn the joint distribution of full data. However, applying advanced deep generative models…
Graph Out-of-Distribution Generalization via Causal Intervention
Qitian Wu, Fan Nie, Chenxiao Yang +2
Out-of-distribution (OOD) generalization has gained increasing attentions for learning on graphs, as graph neural networks (GNNs) often exhibit performance degradation with distrib…
Supercharging Graph Transformers with Advective Diffusion
Qitian Wu, Chenxiao Yang, Kaipeng Zeng +1
The capability of generalization is a cornerstone for the success of modern learning systems. For non-Euclidean data, e.g., graphs, that particularly involves topological structure…
How Graph Neural Networks Learn: Lessons from Training Dynamics
Chenxiao Yang, Qitian Wu, David Wipf +2
A long-standing goal in deep learning has been to characterize the learning behavior of black-box models in a more interpretable manner. For graph neural networks (GNNs), considera…
GraphGLOW: Universal and Generalizable Structure Learning for Graph Neural Networks
Wentao Zhao, Qitian Wu, Chenxiao Yang +1
Graph structure learning is a well-established problem that aims at optimizing graph structures adaptive to specific graph datasets to help message passing neural networks (i.e., G…
NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification
Qitian Wu, Wentao Zhao, Zenan Li +2
Graph neural networks have been extensively studied for learning with inter-connected data. Despite this, recent evidence has revealed GNNs' deficiencies related to over-squashing,…
SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations
Qitian Wu, Wentao Zhao, Chenxiao Yang +5
Learning representations on large-sized graphs is a long-standing challenge due to the inter-dependence nature involved in massive data points. Transformers, as an emerging class o…
Energy-based Out-of-Distribution Detection for Graph Neural Networks
Qitian Wu, Yiting Chen, Chenxiao Yang +1
Learning on graphs, where instance nodes are inter-connected, has become one of the central problems for deep learning, as relational structures are pervasive and induce data inter…
DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion
Qitian Wu, Chenxiao Yang, Wentao Zhao +3
Real-world data generation often involves complex inter-dependencies among instances, violating the IID-data hypothesis of standard learning paradigms and posing a challenge for un…
Localized Contrastive Learning on Graphs
Hengrui Zhang, Qitian Wu, Yu Wang +3
Contrastive learning methods based on InfoNCE loss are popular in node representation learning tasks on graph-structured data. However, its reliance on data augmentation and its qu…
Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPs
Chenxiao Yang, Qitian Wu, Jiahua Wang +1
Graph neural networks (GNNs), as the de-facto model class for representation learning on graphs, are built upon the multi-layer perceptrons (MLP) architecture with additional messa…
Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shift
Yongduo Sui, Qitian Wu, Jiancan Wu +5
The issue of distribution shifts is emerging as a critical concern in graph representation learning. From the perspective of invariant learning and stable learning, a recently well…
Geometric Knowledge Distillation: Topology Compression for Graph Neural Networks
Chenxiao Yang, Qitian Wu, Junchi Yan
We study a new paradigm of knowledge transfer that aims at encoding graph topological information into graph neural networks (GNNs) by distilling knowledge from a teacher GNN model…
Towards Out-of-Distribution Sequential Event Prediction: A Causal Treatment
Chenxiao Yang, Qitian Wu, Qingsong Wen +3
The goal of sequential event prediction is to estimate the next event based on a sequence of historical events, with applications to sequential recommendation, user behavior analys…
Handling Distribution Shifts on Graphs: An Invariance Perspective
Qitian Wu, Hengrui Zhang, Junchi Yan +1
There is increasing evidence suggesting neural networks' sensitivity to distribution shifts, so that research on out-of-distribution (OOD) generalization comes into the spotlight.…
Towards Open-World Feature Extrapolation: An Inductive Graph Learning Approach
Qitian Wu, Chenxiao Yang, Junchi Yan
We target open-world feature extrapolation problem where the feature space of input data goes through expansion and a model trained on partially observed features needs to handle n…
From Canonical Correlation Analysis to Self-supervised Graph Neural Networks
Hengrui Zhang, Qitian Wu, Junchi Yan +2
We introduce a conceptually simple yet effective model for self-supervised representation learning with graph data. It follows the previous methods that generate two views of an in…
Learning Latent Process from High-Dimensional Event Sequences via Efficient Sampling
Qitian Wu, Zixuan Zhang, Xiaofeng Gao +2
We target modeling latent dynamics in high-dimension marked event sequences without any prior knowledge about marker relations. Such problem has been rarely studied by previous wor…