Yiheng Du

5 papers · 2023–2025 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🐣 Hot Topic Early Bird

Venues

ICLR (4) ICML (1)

Top co-authors

Bohang Zhang (3) Liwei Wang (3) Jingchu Gai (2) Aditi S. Krishnapriyan (2) Nithin Chalapathi (2) Di He (2) Guhao Feng (1) Qiwei Ye (1) Haggai Maron (1)

Research topics

Machine Learning (5) Optimization & Theory (5) Deep Learning (3) Architectures (3) Core Methods (3) Artificial Intelligence (1) Application Areas (1) Core AI (1)

Keywords

graph neural network (3) subgraph counting (2) homomorphism expressivity (2) partial differential equation (2) weisfeiler-lehman test (1) expressive power (1) spectral method (1) physics-informed neural network (1) mixture of expert (1) neural operator (1) physics simulation (1) subgraph neural network (1) architecture design (1) differentiable physics (1) subgraph isomorphism (1) spectral loss (1) neural network training (1) spectral invariant (1) constraint optimization (1) graph representation (1)

Papers

Homomorphism Expressivity of Spectral Invariant Graph Neural Networks ICLR 2025 Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness ICLR 2024 Neural Spectral Methods: Self-supervised learning in the spectral domain ICLR 2024 Scaling physics-informed hard constraints with mixture-of-experts ICLR 2024 A Complete Expressiveness Hierarchy for Subgraph GNNs via Subgraph Weisfeiler-Lehman Tests ICML 2023