Hongyang Gao
9 papers · 2018–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
πΊοΈ Taxonomy Completionist (17) π§ Keyword Pioneer π Interdisciplinary Bridge π Conference Polyglot (4) π Academic Marathon (7)
π£
Hot Topic Early Bird
π
Cross-Pollinator
(13)
π
Grand Slam
Conferences
ICLR (3)
NIPS (3)
ICML (2)
AAAI (1)
Top co-authors
Keywords
convolutional neural network
(2)
graph neural network
(2)
multi-task learning
(1)
neural network training
(1)
few-shot learning
(1)
sparse representation
(1)
feature representation
(1)
multi-task feature learning
(1)
gaussian process
(1)
parameter sharing
(1)
learning rate
(1)
node classification
(1)
activation function
(1)
molecular representation learning
(1)
encoder-decoder architecture
(1)
infinite width
(1)
graph pooling
(1)
parameter reduction
(1)
rectified linear unit
(1)
adaptive optimizer
(1)
Papers
Global Convergence in Neural ODEs: Impact of Activation Functions
ICLR 2025
MAGE: Model-Level Graph Neural Networks Explanations via Motif-based Graph Generation
ICLR 2025
Wide Neural Networks as Gaussian Processes: Lessons from Deep Equilibrium Models
NIPS 2023
Meta-AdaM: An Meta-Learned Adaptive Optimizer with Momentum for Few-Shot Learning
NIPS 2023
Molecular Representation Learning via Heterogeneous Motif Graph Neural Networks
ICML 2022
A global convergence theory for deep ReLU implicit networks via over-parameterization
ICLR 2022
Adaptive Convolutional ReLUs
AAAI 2020
Graph U-Nets
ICML 2019
ChannelNets: Compact and Efficient Convolutional Neural Networks via Channel-Wise Convolutions
NIPS 2018