Jiaqi Han

I am currently a second year PhD student at Stanford Computer Science, advised by Prof. Stefano Ermon. Previously, I obtained B.S. in Computer Science at Tsinghua University, where I was very fortunate to work with Prof. Wenbing Huang during my undergrad.

My core research interests lie in developing generative models for data with irregular structures: discrete data (texts), temporal data (trajectories and videos), relational data (graphs), and geometric data (molecules and proteins), to name a few.

Welcome to drop me an email if you want to discuss or collaborate!

news

Nov 20, 2022	Our team received the first place of NeurIPS’22 Open Catalyst Challenge, and was invited for the winner’s talk at the event!
Sep 25, 2022	Two papers on equivariant GNNs for science (EGHN, SGNN) have been accepted by NeurIPS 2022.
Jan 30, 2022	Equivariant Graph Mechanics Networks has been accepted by ICLR 2022.

selected publications [full list]

(*) denotes equal contribution

NeurIPS

Geometric Trajectory Diffusion Models

Jiaqi Han, Minkai Xu, Aaron Lou, Haotian Ye, and Stefano Ermon

Advances in Neural Information Processing Systems, 2024

PDF Code
NeurIPS

TFG: Unified Training-Free Guidance for Diffusion Models

Haotian Ye*, Haowei Lin*, Jiaqi Han*, Minkai Xu, Sheng Liu, Yitao Liang, Jianzhu Ma, James Zou, and Stefano Ermon

Advances in Neural Information Processing Systems, 2024

PDF
ICML

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

In Forty-first International Conference on Machine Learning, 2024

PDF Code
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
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.
Equivariant graph hierarchy-based neural networks

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

Advances in Neural Information Processing Systems, 2022

PDF Code
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
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
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.