Junchi Yu

I am a 5th-year Ph.D. candidate at the Insititute of Automation, Chinese Academy of Sciences, advised by Prof. Ran He.

Previouly, I was a research intern at Tencent AI LAB, working with Dr. Tingyang Xu, Dr. Yu Rong, Dr. Yatao Bian and Prof. Junzhou Huang. I was a visiting student at the Department of Computer Science, Yale University, working with Prof. Rex Ying.

I aim to develop Trustworthy Graph Learning (TwGL) methods with good interpretability and transferability, and explore their biochemistry applications. Recently I also try to extend the success in graph learning to complex reasoning with Large Language Models (LLMs).


profile photo
Publications ( Full Publication List )
lft Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language Models
Junchi Yu, Ran He, Rex Ying
ICLR, 2024  
PDF / Code

Improve the complex reasoning ability of LLMs in the graph, text, and 3D world by analogical reasoning.

lft Rumor Detection with Diverse Counterfactual Evidences
Kaiwei Zhang, Junchi Yu, Haichao Shi, Jian Liang, Xiaoyu Zhang
KDD, 2023  
PDF / Code

A Robust and Interpretable Rumor Detection Method by Exploiting Diverse Counterfactual Evidences.

lft LiSA: Mind the Label-shift of Augmentation-based Graph OOD Generalization
Junchi Yu, Jian Liang, Ran He
CVPR, 2023  
PDF / Code

Practical Label-invariant Augmentation Framework for Graph Out-of-Distribution Generalization By Discovery of Diverse Label-invariant Subgraphs.

lft Structure-aware conditional variational auto-encoder for constrained molecule optimization
Junchi Yu, Tingyang Xu, Yu Rong, Junzhou Huang, Ran He
Pattern Recognition, 2022  

VAE-based Molecule Optimization Framework with Limited Structural Modification to the Input Molecules.

lft Improving Subgraph Recognition with Variational Graph Information Bottleneck
Junchi Yu, Jie Cao, Ran He
CVPR, 2022  
PDF / Code

A variational framework of our prior GIB with improved stability and training efficiency.

lft Recognizing Predictive Substructures with Subgraph Information Bottleneck
Junchi Yu, Tingyang Xu, Yu Rong, Yatao Bian, Junzhou Huang, Ran He
IEEE Transactions on Pattern Analysis and Machine Intelligence, 2021  
PDF / Code

An extended publication of GIB with more theoretic analysis on IB-Subgraph properties and the GIB optimization strategy.

lft Graph Information Bottleneck for Subgraph Recognition
Junchi Yu, Tingyang Xu, Yu Rong, Yatao Bian, Junzhou Huang, Ran He
ICLR, 2021  
PDF / Code

An Information-theoretic framwork, namely Graph Information Bottleneck, for interpretable and robust graph learning.

lft Pose-preserving Cross Spectral Face Hallucination
Junchi Yu, Jie Cao, Yi Li, Xiaofei Jia, Ran He
IJCAI, 2019  

A generative framework for cross-domain face recognition.

Academic Service

Trustworthy Graph Learning: Reliability, Explainability, and Privacy Protection @ KDD 2022,
Advanced Deep Graph Learning: Deeper, Faster, Robuster, and Unsupervised @ WWW 2021.

Journals: IEEE Transactions on Pattern Analysis and Machine Intelligence, Pattern Recognition.
Conferences: ICML, NeurIPS, ICLR, CVPR, Ph.D. Consortium@KDD.

Flag Counter

Last updated June 2023.
Template from Jon Barron.