649 citations · 1.8k across the 42 of their papers we have counts for
42 papers
EquiPocket: an E(3)-Equivariant Geometric Graph Neural Network for Ligand Binding Site Prediction
Yang Zhang, Zhewei Wei, Ye Yuan +2
Predicting the binding sites of target proteins plays a fundamental role in drug discovery. Most existing deep-learning methods consider a protein as a 3D image by spatially cluste…
End-to-End Full-Atom Antibody Design
Xiangzhe Kong, Wenbing Huang, Yang Liu
Antibody design is an essential yet challenging task in various domains like therapeutics and biology. There are two major defects in current learning-based methods: 1) tackling on…
Learning Active Camera for Multi-Object Navigation
Peihao Chen, Dongyu Ji, Kunyang Lin +5
Getting robots to navigate to multiple objects autonomously is essential yet difficult in robot applications. One of the key challenges is how to explore environments efficiently w…
Learning Physical Dynamics with Subequivariant Graph Neural Networks
Jiaqi Han, Wenbing Huang, Hengbo Ma +3
Graph Neural Networks (GNNs) have become a prevailing tool for learning physical dynamics. However, they still encounter several challenges: 1) Physical laws abide by symmetry, whi…
Benefits of Permutation-Equivariance in Auction Mechanisms
Tian Qin, Fengxiang He, Dingfeng Shi +2
Designing an incentive-compatible auction mechanism that maximizes the auctioneer's revenue while minimizes the bidders' ex-post regret is an important yet intricate problem in eco…
Conditional Antibody Design as 3D Equivariant Graph Translation
Xiangzhe Kong, Wenbing Huang, Yang Liu
Antibody design is valuable for therapeutic usage and biological research. Existing deep-learning-based methods encounter several key issues: 1) incomplete context for Complementar…
Energy-Motivated Equivariant Pretraining for 3D Molecular Graphs
Rui Jiao, Jiaqi Han, Wenbing Huang +2
Pretraining molecular representation models without labels is fundamental to various applications. Conventional methods mainly process 2D molecular graphs and focus solely on 2D ta…
Smoothing Matters: Momentum Transformer for Domain Adaptive Semantic Segmentation
Runfa Chen, Yu Rong, Shangmin Guo +4
After the great success of Vision Transformer variants (ViTs) in computer vision, it has also demonstrated great potential in domain adaptive semantic segmentation. Unfortunately,…
Sound Adversarial Audio-Visual Navigation
Yinfeng Yu, Wenbing Huang, Fuchun Sun +3
Audio-visual navigation task requires an agent to find a sound source in a realistic, unmapped 3D environment by utilizing egocentric audio-visual observations. Existing audio-visu…
Geometrically Equivariant Graph Neural Networks: A Survey
Jiaqi Han, Yu Rong, Tingyang Xu +1
Many scientific problems require to process data in the form of geometric graphs. Unlike generic graph data, geometric graphs exhibit symmetries of translations, rotations, and/or…
Transformer for Graphs: An Overview from Architecture Perspective
Erxue Min, Runfa Chen, Yatao Bian +7
Recently, Transformer model, which has achieved great success in many artificial intelligence fields, has demonstrated its great potential in modeling graph-structured data. Till n…
Sim2Real Object-Centric Keypoint Detection and Description
Chengliang Zhong, Chao Yang, Jinshan Qi +4
Keypoint detection and description play a central role in computer vision. Most existing methods are in the form of scene-level prediction, without returning the object classes of…
Equivariant Graph Hierarchy-Based Neural Networks
Jiaqi Han, Wenbing Huang, Tingyang Xu +1
Equivariant Graph neural Networks (EGNs) are powerful in characterizing the dynamics of multi-body physical systems. Existing EGNs conduct flat message passing, which, yet, is unab…
Channel Exchanging Networks for Multimodal and Multitask Dense Image Prediction
Yikai Wang, Fuchun Sun, Wenbing Huang +2
Multimodal fusion and multitask learning are two vital topics in machine learning. Despite the fruitful progress, existing methods for both problems are still brittle to the same c…
Graph Convolutional Module for Temporal Action Localization in Videos
Runhao Zeng, Wenbing Huang, Mingkui Tan +4
Temporal action localization has long been researched in computer vision. Existing state-of-the-art action localization methods divide each video into multiple action units (i.e.,…
Elastic Tactile Simulation Towards Tactile-Visual Perception
Yikai Wang, Wenbing Huang, Bin Fang +2
Tactile sensing plays an important role in robotic perception and manipulation tasks. To overcome the real-world limitations of data collection, simulating tactile response in a vi…
Adversarial Option-Aware Hierarchical Imitation Learning
Mingxuan Jing, Wenbing Huang, Fuchun Sun +4
It has been a challenge to learning skills for an agent from long-horizon unannotated demonstrations. Existing approaches like Hierarchical Imitation Learning(HIL) are prone to com…
Molecule Generation by Principal Subgraph Mining and Assembling
Xiangzhe Kong, Wenbing Huang, Zhixing Tan +1
Molecule generation is central to a variety of applications. Current attention has been paid to approaching the generation task as subgraph prediction and assembling. Nevertheless,…
Noise-robust Graph Learning by Estimating and Leveraging Pairwise Interactions
Xuefeng Du, Tian Bian, Yu Rong +6
Teaching Graph Neural Networks (GNNs) to accurately classify nodes under severely noisy labels is an important problem in real-world graph learning applications, but is currently u…
Adversarial Attack Framework on Graph Embedding Models with Limited Knowledge
Heng Chang, Yu Rong, Tingyang Xu +6
With the success of the graph embedding model in both academic and industry areas, the robustness of graph embedding against adversarial attack inevitably becomes a crucial problem…
Deep Multimodal Fusion by Channel Exchanging
Yikai Wang, Wenbing Huang, Fuchun Sun +3
Deep multimodal fusion by using multiple sources of data for classification or regression has exhibited a clear advantage over the unimodal counterpart on various applications. Yet…
Tackling Over-Smoothing for General Graph Convolutional Networks
Wenbing Huang, Yu Rong, Tingyang Xu +2
Increasing the depth of GCN, which is expected to permit more expressivity, is shown to incur performance detriment especially on node classification. The main cause of this lies i…
Towards Purely Unsupervised Disentanglement of Appearance and Shape for Person Images Generation
Hongtao Yang, Tong Zhang, Wenbing Huang +2
There have been a fairly of research interests in exploring the disentanglement of appearance and shape from human images. Most existing endeavours pursuit this goal by either usin…
Inverse Graph Identification: Can We Identify Node Labels Given Graph Labels?
Tian Bian, Xi Xiao, Tingyang Xu +4
Graph Identification (GI) has long been researched in graph learning and is essential in certain applications (e.g. social community detection). Specifically, GI requires to predic…