Yangkun Wang
9 papers · 2021–2025 · 7 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 · Silver
🌉
Interdisciplinary Bridge · Silver
🗺️
Taxonomy Completionist
(23)
🔥
Unstoppable · Bronze
❓
The Questioner
(2)
Top co-authors
Research topics
Machine Learning
(8)
Deep Learning
(7)
Core Methods
(7)
Architectures
(4)
Artificial Intelligence
(3)
Core AI
(3)
Learning Types · Deep Learning
(3)
Optimization & Theory
(3)
Natural Language Processing
(2)
Learning Types · Machine Learning
(2)
Interdisciplinary
(1)
Mathematics & Optimization
(1)
Applications
(1)
Learning Paradigms
(1)
Optimization
(1)
Keywords
graph neural network
(6)
node classification
(3)
representation learning
(2)
text classification
(2)
tabular data
(2)
message passing
(1)
sentiment analysis
(1)
semi-supervised learning
(1)
toxicity detection
(1)
attention mechanism
(1)
content moderation
(1)
responsible ai
(1)
ensemble learning
(1)
proximal gradient descent
(1)
convergence guarantee
(1)
gradient-based optimization
(1)
knowledge graph
(1)
deep equilibrium model
(1)
language model
(1)
relation prediction
(1)
Papers
Direct Prompt Optimization with Continuous Representations
ACL 2025
Implicit vs Unfolded Graph Neural Networks
JMLR 2025
Towards Few-shot Entity Recognition in Document Images: A Graph Neural Network Approach Robust to Image Manipulation
COLING 2024
ToxicChat: Unveiling Hidden Challenges of Toxicity Detection in Real-World User-AI Conversation
EMNLP 2023
Does your graph need a confidence boost? Convergent boosted smoothing on graphs with tabular node features
ICLR 2022
Inductive Relation Prediction Using Analogy Subgraph Embeddings
ICLR 2022
Learning Enhanced Representation for Tabular Data via Neighborhood Propagation
NeurIPS 2022
Why Propagate Alone? Parallel Use of Labels and Features on Graphs
ICLR 2022
Graph Neural Networks Inspired by Classical Iterative Algorithms
ICML 2021