Fanchen Bu
8 papers · 2022–2025 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+3 more ↓ Show less ↑
π§ Keyword Pioneer π Interdisciplinary Bridge π Renaissance Researcher (5) πΊοΈ Taxonomy Completionist (17) π Conference Polyglot (4)
π
Cross-Pollinator
(13)
π
Grand Slam
π
Triple Crown
Conferences
ICML (4)
AAAI (2)
ICLR (1)
NIPS (1)
Top co-authors
Research topics
Keywords
graph neural network
(2)
gradient descent
(2)
anomaly detection
(1)
graph anomaly detection
(1)
attention mechanism
(1)
graph representation
(1)
neural network optimization
(1)
graph attention
(1)
reconstruction error
(1)
deep architecture
(1)
continuous relaxation
(1)
deep neural network
(1)
node classification
(1)
differentiable optimization
(1)
numerical stability
(1)
graph autoencoder
(1)
stiefel manifold
(1)
orthogonality constraint
(1)
orthogonal constraint
(1)
deep representation
(1)
Papers
DiffIM: Differentiable Influence Minimization with Surrogate Modeling and Continuous Relaxation
AAAI 2025
Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification
ICML 2025
Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedy
NIPS 2024
HypeBoy: Generative Self-Supervised Representation Learning on Hypergraphs
ICLR 2024
Tackling Prevalent Conditions in Unsupervised Combinatorial Optimization: Cardinality, Minimum, Covering, and More
ICML 2024
Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspective
ICML 2024
Towards Deep Attention in Graph Neural Networks: Problems and Remedies
ICML 2023
Feedback Gradient Descent: Efficient and Stable Optimization with Orthogonality for DNNs
AAAI 2022