Hongkang Li
9 papers · 2022–2025 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π£ Hot Topic Early Bird π Interdisciplinary Bridge π§ Keyword Pioneer πΊοΈ Taxonomy Completionist (12) π Conference Polyglot (3)
π
Cross-Pollinator
(11)
β
The Questioner
(3)
Conferences
ICLR (4)
ICML (3)
NIPS (2)
Top co-authors
Keywords
sample complexity
(2)
non-convex optimization
(1)
graph classification
(1)
convergence analysis
(1)
graph representation
(1)
inductive bia
(1)
graph transformer
(1)
generalization guarantee
(1)
node classification
(1)
positional encoding
(1)
hierarchical distance encoding
(1)
graph convolutional network
(1)
semi-supervised node classification
(1)
deep q-network
(1)
epsilon-greedy exploration
(1)
topology sampling
(1)
reinforcement learning
(1)
graph topology sampling
(1)
Papers
Node Identifiers: Compact, Discrete Representations for Efficient Graph Learning
ICLR 2025
When is Task Vector Provably Effective for Model Editing? A Generalization Analysis of Nonlinear Transformers
ICLR 2025
Training Nonlinear Transformers for Chain-of-Thought Inference: A Theoretical Generalization Analysis
ICLR 2025
What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding
ICML 2024
Enhancing Graph Transformers with Hierarchical Distance Structural Encoding
NIPS 2024
How Do Nonlinear Transformers Learn and Generalize in In-Context Learning?
ICML 2024
On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\epsilon$-Greedy Exploration
NIPS 2023
A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity
ICLR 2023
Generalization Guarantee of Training Graph Convolutional Networks with Graph Topology Sampling
ICML 2022