Chuxu Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Chuxu Zhang has a total of 118 co-authors. Here are the top co-authors by number of shared publications:
- Nitesh V. Chawla
University of Notre Dame, Notre Dame, Indiana, USA
16 shared publications - Jundong Li
University of Virginia
10 shared publications - Yanfang Ye
Department of Computer Science and Engineering, University of Notre Dame, Notre Dame, Indiana, USA
10 shared publications - Kaize Ding
Northwestern University, Evanston, IL, USA
8 shared publications - Xiangliang Zhang
University of Notre Dame
7 shared publications - Zehong Wang
University of Notre Dame, Notre Dame, IN, USA
7 shared publications
Latest Publications
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 13451-13452
RelKD 2026: The Fourth International Workshop on Resource-Efficient Learning for Knowledge Discovery
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 13451-13452
Open AccessRelKD 2026: The Fourth International Workshop on Resource-Efficient Learning for Knowledge Discovery
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1474-1485
Generalizing GNNs with Tokenized Mixture of Experts
Deployed graph neural networks (GNNs) operate as frozen snapshots, yet must simultaneously fit clean data, generalize under distribution shifts, and remain stable against input perturbations---three goals that are difficult to satisfy at once with a single fixed model. We first show theoretically that a single fixed inference rule can create a stability--generalization tradeoff: making the model insensitive to perturbations can also suppress task-relevant signals needed to fit and generalize. Input-dependent routing---assigning different computation paths to different inputs---can relax this tension, but brings new fragility: distribution shifts may mislead routing decisions, and perturbations can destabilize routing, compounding downstream errors. We formalize these effects through two risk decompositions that separate (i) how well the available paths cover diverse test conditions from how accurately the router selects among them, and (ii)~how sensitive each fixed path is from how much routing fluctuation amplifies that sensitivity. Guided by these analyses, we propose STEM-GNN: Stable TokEnized Mixture-of-Experts GNN, a pretrain-then-finetune framework that couples a mixture-of-experts encoder providing diverse computation paths to cover heterogeneous test conditions, a vector-quantized token interface that maps encoder outputs to a discrete codebook to absorb small representation drift induced by input perturbations and routing fluctuations before downstream layers, and a Lipschitz-regularized prediction head that bounds how much the output can amplify residual upstream variation. Across eight node, link, and graph benchmarks, STEM-GNN maintains strong clean performance; on representative node benchmarks, it improves the three-way balance under degree/homophily shifts and feature/edge perturbations. The code and data are available at https://github.com/GXG-CS/STEM-GNN.
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 1474-1485
Open AccessGeneralizing GNNs with Tokenized Mixture of Experts
Deployed graph neural networks (GNNs) operate as frozen snapshots, yet must simultaneously fit clean data, generalize under distribution shifts, and remain stable against input perturbations---three goals that are difficult to satisfy at once with a single fixed model. We first show theoretically that a single fixed inference rule can create a stability--generalization tradeoff: making the model insensitive to perturbations can also suppress task-relevant signals needed to fit and generalize. Input-dependent routing---assigning different computation paths to different inputs---can relax this tension, but brings new fragility: distribution shifts may mislead routing decisions, and perturbations can destabilize routing, compounding downstream errors. We formalize these effects through two risk decompositions that separate (i) how well the available paths cover diverse test conditions from how accurately the router selects among them, and (ii)~how sensitive each fixed path is from how much routing fluctuation amplifies that sensitivity. Guided by these analyses, we propose STEM-GNN: Stable TokEnized Mixture-of-Experts GNN, a pretrain-then-finetune framework that couples a mixture-of-experts encoder providing diverse computation paths to cover heterogeneous test conditions, a vector-quantized token interface that maps encoder outputs to a discrete codebook to absorb small representation drift induced by input perturbations and routing fluctuations before downstream layers, and a Lipschitz-regularized prediction head that bounds how much the output can amplify residual upstream variation. Across eight node, link, and graph benchmarks, STEM-GNN maintains strong clean performance; on representative node benchmarks, it improves the three-way balance under degree/homophily shifts and feature/edge perturbations. The code and data are available at https://github.com/GXG-CS/STEM-GNN.
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 9534-9545
OPBench: A Graph Benchmark to Combat the Opioid Crisis
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 9534-9545
Open AccessOPBench: A Graph Benchmark to Combat the Opioid Crisis
- Open Access
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 13135-13146
MUSTANG: Multi-Variable Spatio-Temporal Meta-Learning for Water Data Imputation
- 8 August 2026
- Published by Association for Computing Machinery (ACM)
- p. 13135-13146
Open AccessMUSTANG: Multi-Variable Spatio-Temporal Meta-Learning for Water Data Imputation
- Open Access
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1195-1205
Controllable Graph Generation with Diffusion Models via Inference-Time Tree Search Guidance
- 12 April 2026
- Published by Association for Computing Machinery (ACM)
- p. 1195-1205
Open AccessControllable Graph Generation with Diffusion Models via Inference-Time Tree Search Guidance
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 6010-6020
Graph Prompting for Graph Learning Models: Recent Advances and Future Directions
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 6010-6020
Open AccessGraph Prompting for Graph Learning Models: Recent Advances and Future Directions
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 6184-6194
Graph Foundation Models: Challenges, Methods, and Open Questions
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 6184-6194
Open AccessGraph Foundation Models: Challenges, Methods, and Open Questions
- Open Access
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 6308-6309
RelKD 2025: The Third International Workshop on Resource-Efficient Learning for Knowledge Discovery
- 3 August 2025
- Published by Association for Computing Machinery (ACM)
- p. 6308-6309
Open AccessRelKD 2025: The Third International Workshop on Resource-Efficient Learning for Knowledge Discovery
- Open Access
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2860-2871
MOPI-HFRS: A Multi-objective Personalized Health-aware Food Recommendation System with LLM-enhanced Interpretation
- 20 July 2025
- Published by Association for Computing Machinery (ACM)
- p. 2860-2871
Open AccessMOPI-HFRS: A Multi-objective Personalized Health-aware Food Recommendation System with LLM-enhanced Interpretation
- Open Access
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 2468-2471
RelWeb 2025: The International Workshop on Resource-Efficient Learning for the Web
- 8 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 2468-2471
Open AccessRelWeb 2025: The International Workshop on Resource-Efficient Learning for the Web