publications

2024

1. Arxiv

   Equivariant Graph Neural Operator for Modeling 3D Dynamics

   Minkai Xu*, Jiaqi Han*, Aaron Lou, Jean Kossaifi, Arvind Ramanathan, Kamyar Azizzadenesheli, Jure Leskovec, Stefano Ermon, and Anima Anandkumar

   arXiv preprint arXiv:2401.11037, 2024

   PDF Code

2023

1. NeurIPS

   Crystal structure prediction by joint equivariant diffusion

   Rui Jiao, Wenbing Huang, Peijia Lin, Jiaqi Han, Pin Chen, Yutong Lu, and Yang Liu

   Advances in Neural Information Processing Systems, 2023

   PDF Code
2. IEEE TNNLS

   Structure-Aware DropEdge Toward Deep Graph Convolutional Networks

   Jiaqi Han, Wenbing Huang, Yu Rong, Tingyang Xu, Fuchun Sun, and Junzhou Huang

   IEEE Transactions on Neural Networks and Learning Systems, 2023

   PDF Code
3. ICML
   Oral

   Subequivariant Graph Reinforcement Learning in 3D Environments

   Runfa Chen*, Jiaqi Han*, Fuchun Sun, and Wenbing Huang

   In Proceedings of the 40th International Conference on Machine Learning, 2023

   Oral Presentation [Top 2.3%]

   Abs PDF Code Website

   Learning a shared policy that guides the locomotion of different agents is of core interest in Reinforcement Learning (RL), which leads to the study of morphology-agnostic RL. However, existing benchmarks are highly restrictive in the choice of starting point and target point, constraining the movement of the agents within 2D space. In this work, we propose a novel setup for morphology-agnostic RL, dubbed Subequivariant Graph RL in 3D environments (3D-SGRL). Specifically, we first introduce a new set of more practical yet challenging benchmarks in 3D space that allows the agent to have full Degree-of-Freedoms to explore in arbitrary directions starting from arbitrary configurations. Moreover, to optimize the policy over the enlarged state-action space, we propose to inject geometric symmetry, i.e., subequivariance, into the modeling of the policy and Q-function such that the policy can generalize to all directions, improving exploration efficiency. This goal is achieved by a novel SubEquivariant Transformer (SET) that permits expressive message exchange. Finally, we evaluate the proposed method on the proposed benchmarks, where our method consistently and significantly outperforms existing approaches on single-task, multi-task, and zero-shot generalization scenarios. Extensive ablations are also conducted to verify our design.

4. AAAI

   Energy-motivated equivariant pretraining for 3d molecular graphs

   Rui Jiao, Jiaqi Han, Wenbing Huang, Yu Rong, and Yang Liu

   In Proceedings of the AAAI Conference on Artificial Intelligence, 2023

   PDF Code

2022

1. 

   Equivariant graph hierarchy-based neural networks

   Jiaqi Han, Wenbing Huang, Tingyang Xu, and Yu Rong

   Advances in Neural Information Processing Systems, 2022

   PDF Code

2. 

   Learning physical dynamics with subequivariant graph neural networks

   Jiaqi Han, Wenbing Huang, Hengbo Ma, Jiachen Li, Josh Tenenbaum, and Chuang Gan

   Advances in Neural Information Processing Systems, 2022

   PDF Code Website
3. Arxiv

   Geometrically equivariant graph neural networks: A survey

   Jiaqi Han, Yu Rong, Tingyang Xu, and Wenbing Huang

   arXiv preprint arXiv:2202.07230, 2022

   PDF
4. ICLR

   Equivariant Graph Mechanics Networks with Constraints

   Wenbing Huang*, Jiaqi Han*, Yu Rong, Tingyang Xu, Fuchun Sun, and Junzhou Huang

   In International Conference on Learning Representations, 2022

   PDF Code
5. Arxiv

   Smoothing matters: Momentum transformer for domain adaptive semantic segmentation

   Runfa Chen, Yu Rong, Shangmin Guo, Jiaqi Han, Fuchun Sun, Tingyang Xu, and Wenbing Huang

   arXiv preprint arXiv:2203.07988, 2022

   PDF Code

2021

1. KDD

   Multivariate Time Series Anomaly Detection and Interpretation Using Hierarchical Inter-Metric and Temporal Embedding

   Zhihan Li, Youjian Zhao, Jiaqi Han, Ya Su, Rui Jiao, Xidao Wen, and Dan Pei

   In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, 2021

   Abs PDF Code

   Anomaly detection is a crucial task for monitoring various status (i.e., metrics) of entities (e.g., manufacturing systems and Internet services), which are often characterized by multivariate time series (MTS). In practice, it’s important to precisely detect the anomalies, as well as to interpret the detected anomalies through localizing a group of most anomalous metrics, to further assist the failure troubleshooting. In this paper, we propose InterFusion, an unsupervised method that simultaneously models the inter-metric and temporal dependency for MTS. Its core idea is to model the normal patterns inside MTS data through hierarchical Variational AutoEncoder with two stochastic latent variables, each of which learns low-dimensional inter-metric or temporal embeddings. Furthermore, we propose an MCMC-based method to obtain reasonable embeddings and reconstructions at anomalous parts for MTS anomaly interpretation. Our evaluation experiments are conducted on four real-world datasets from different industrial domains (three existing and one newly published dataset collected through our pilot deployment of InterFusion). InterFusion achieves an average anomaly detection F1-Score higher than 0.94 and anomaly interpretation performance of 0.87, significantly outperforming recent state-of-the-art MTS anomaly detection methods.