Do Transformers Really Perform Badly for Graph Representation

Chengxuan Ying, Tianle Cai, Shengjie Luo, +5

Neural Information Processing Systems

EngineeringGraph TheoryData SciencePerform BadlyNetwork Analysis +3

Do Transformers Really Perform Bad for Graph Representation?

Chengxuan Ying, Tianle Cai, Shengjie Luo, +5

arXiv (Cornell University)

Natural Language ProcessingGeometric LearningStructural InformationGraph Representation LearningGraph Theory +13

Adversarially Robust Generalization Just Requires More Unlabeled Data

Runtian Zhai, Tianle Cai, Di He, +4

arXiv (Cornell University)

Artificial IntelligenceNeural Network RobustnessEngineeringMachine LearningData Science +11

GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training

Tianle Cai, Shengjie Luo, Keyulu Xu, +3

arXiv (Cornell University)

Geometric LearningDeep Neural NetworksGraph Neural NetworksGraph TheoryMachine Learning +12

Convergence of Adversarial Training in Overparametrized Neural Networks

Ruiqi Gao, Tianle Cai, Haochuan Li, +3

arXiv (Cornell University)

Artificial IntelligenceHyperparameter EstimationEngineeringMachine LearningComputational Learning Theory +9

Towards a Theoretical Framework of Out-of-Distribution Generalization

Haotian Ye, Chuanlong Xie, Tianle Cai, +3

arXiv (Cornell University)

EngineeringMachine LearningData SciencePattern RecognitionStatistics +14

Gram-Gauss-Newton Method: Learning Overparameterized Neural Networks for Regression Problems

Tianle Cai, Ruiqi Gao, Jikai Hou, +5

arXiv (Cornell University)

Artificial IntelligenceModel OptimizationHyperparameter EstimationEngineeringMachine Learning +10

DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models

Muyang Li, Tianle Cai, Jiaxin Cao, +6

Convergence of Adversarial Training in Overparametrized Neural Networks

Ruiqi Gao, Tianle Cai, Haochuan Li, +3

arXiv (Cornell University)

Artificial IntelligenceSurrogate LossHyperparameter EstimationEngineeringMachine Learning +11

What Makes Convolutional Models Great on Long Sequence Modeling?

Yuhong Li, Tianle Cai, Yi Zhang, +2

arXiv (Cornell University)

Convolutional Neural NetworkEngineeringMachine LearningRecurrent Neural NetworkConvolution Kernel +15