Jiansheng Yang
8 papers · 2021–2026 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🏃
Academic Marathon · Sprint
🗺️
Taxonomy Completionist
(13)
Venues
Top co-authors
Research topics
Deep Learning
(6)
Machine Learning
(6)
Core Methods
(4)
Learning Types · Machine Learning
(4)
Architectures
(3)
Techniques
(3)
Artificial Intelligence
(1)
Bayesian & Probabilistic
(1)
Learning Types · Deep Learning
(1)
Models
(1)
Optimization & Theory · Deep Learning
(1)
Optimization & Theory · Machine Learning
(1)
Keywords
contrastive learning
(3)
self-supervised learning
(3)
adversarial training
(2)
graph neural network
(2)
convex optimization
(1)
graph classification
(1)
data augmentation
(1)
minimax optimization
(1)
kernel approximation
(1)
message passing
(1)
excess risk
(1)
graph diffusion
(1)
generative model
(1)
learning rate
(1)
node classification
(1)
energy-based model
(1)
multi-view representation learning
(1)
semantic shift
(1)
robust overfitting
(1)
graph convolutional network
(1)
Papers
Learning Expressive Random Feature Models via Parametrized Activations
UAI 2026
A Message Passing Perspective on Learning Dynamics of Contrastive Learning
ICLR 2023
Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspective
NeurIPS 2023
A Unified Contrastive Energy-based Model for Understanding the Generative Ability of Adversarial Training
ICLR 2022
Chaos is a Ladder: A New Theoretical Understanding of Contrastive Learning via Augmentation Overlap
ICLR 2022
Optimization-Induced Graph Implicit Nonlinear Diffusion
ICML 2022
Dissecting the Diffusion Process in Linear Graph Convolutional Networks
NeurIPS 2021
Residual Relaxation for Multi-view Representation Learning
NeurIPS 2021