On the neural tangent kernel of deep networks with orthogonal initialization W Huang, W Du, RY Da Xu IJCAI 2021, 2020 | 29 | 2020 |
Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective W Huang, Y Li, W Du, RY Da Xu, J Yin, L Chen, M Zhang ICLR 2022, 2021 | 26 | 2021 |
Auto-scaling Vision Transformers without Training W Chen, W Huang, X Du, X Song, Z Wang, D Zhou ICLR 2022, 2022 | 25 | 2022 |
Deep Active Learning by Leveraging Training Dynamics H Wang, W Huang, A Margenot, H Tong, J He NeurIPS 2022, 2021 | 24 | 2021 |
Critical percolation clusters in seven dimensions and on a complete graph W Huang, P Hou, J Wang, RM Ziff, Y Deng Physical Review E 97 (2), 022107, 2018 | 24 | 2018 |
Augmentation-free graph contrastive learning with performance guarantee H Wang, J Zhang, Q Zhu, W Huang* TMLR 2023, 2022 | 22 | 2022 |
On the Equivalence between Neural Network and Support Vector Machine Y Chen, W Huang, LM Nguyen, TW Weng NeurIPS 2021, 2021 | 20 | 2021 |
Adaptive multi-GPU exchange Monte Carlo for the 3D random field Ising model CA Navarro, W Huang, Y Deng Computer Physics Communications 205, 48-60, 2016 | 17 | 2016 |
Understanding and improving feature learning for out-of-distribution generalization Y Chen*, W Huang*, K Zhou*, Y Bian, B Han, J Cheng NeurIPS 2023, 2024 | 16 | 2024 |
Single-pass contrastive learning can work for both homophilic and heterophilic graph H Wang, J Zhang, Q Zhu, W Huang, K Kawaguchi, X Xiao arXiv preprint arXiv:2211.10890, 2022 | 15* | 2022 |
Pruning graph neural networks by evaluating edge properties L Wang, W Huang, M Zhang, S Pan, X Chang, SW Su Knowledge-Based Systems 256, 109847, 2022 | 13 | 2022 |
Earthfarsser: Versatile spatio-temporal dynamical systems modeling in one model H Wu, Y Liang, W Xiong, Z Zhou, W Huang, S Wang, K Wang AAAI 2024 38 (14), 15906-15914, 2024 | 12 | 2024 |
Analyzing Deep PAC-Bayesian Learning with Neural Tangent Kernel: Convergence, Analytic Generalization Bound, and Efficient Hyperparameter Selection W Huang, C Liu, Y Chen, RY Da Xu, M Zhang, TW Weng Transactions on Machine Learning Research, 2023 | 9* | 2023 |
Connection Sensitivity Matters for Training-free DARTS: From Architecture-Level Scoring to Operation-Level Sensitivity Analysis M Zhang, W Huang, L Wang arXiv preprint arXiv:2106.11542, 2021 | 8* | 2021 |
Graph Neural Networks Provably Benefit from Structural Information: A Feature Learning Perspective W Huang, Y Cao, H Wang, X Cao, T Suzuki ICML 2023 HiLD Workshop (Oral), 2023 | 7 | 2023 |
Implicit bias of deep linear networks in the large learning rate phase W Huang, W Du, RY Da Xu, C Liu arXiv preprint arXiv:2011.12547, 2020 | 7* | 2020 |
Mean field theory for deep dropout networks: digging up gradient backpropagation deeply W Huang, RYD Xu, W Du, Y Zeng, Y Zhao ECAI 2020, 2020 | 7 | 2020 |
Deep relu networks have surprisingly simple polytopes FL Fan, W Huang, X Zhong, L Ruan, T Zeng, H Xiong, F Wang arXiv preprint arXiv:2305.09145, 2023 | 6 | 2023 |
Understanding Convergence and Generalization in Federated Learning through Feature Learning Theory W Huang, Y Shi, Z Cai, T Suzuki ICLR 2024, 2023 | 5 | 2023 |
Graph Lottery Ticket Automated G Zhang, K Wang, W Huang, Y Yue, Y Wang, R Zimmermann, A Zhou, ... ICLR 2024, 2023 | 5 | 2023 |