Fanchen Bu
8 papers · 2022–2025 · 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 ↓+1 more ↓ Show less ↑
π Conference Polyglot Β· Bronze π Interdisciplinary Bridge Β· Bronze πΊοΈ Taxonomy Completionist (18) π£ Hot Topic Early Bird π Grand Slam
π
Triple Crown
Venues
Top co-authors
Research topics
Deep Learning
(7)
Machine Learning
(7)
Architectures
(5)
Core Methods
(4)
Optimization & Theory Β· Machine Learning
(3)
Knowledge & Reasoning
(2)
Mathematics & Optimization
(2)
Optimization
(2)
Optimization & Theory Β· Deep Learning
(2)
Representation
(2)
Artificial Intelligence
(1)
Computer Vision
(1)
Analysis
(1)
Application Areas
(1)
Core AI
(1)
Keywords
node classification
(3)
representation learning
(2)
graph neural network
(2)
gradient descent
(2)
attention mechanism
(1)
graph representation
(1)
anomaly detection
(1)
graph convolution
(1)
self-supervised learning
(1)
sparsity
(1)
reconstruction error
(1)
deep architecture
(1)
continuous relaxation
(1)
generative model
(1)
differentiable optimization
(1)
graph attention
(1)
deep neural network
(1)
numerical stability
(1)
neural network optimization
(1)
graph anomaly detection
(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
Feature Distribution on Graph Topology Mediates the Effect of Graph Convolution: Homophily Perspective
ICML 2024
HypeBoy: Generative Self-Supervised Representation Learning on Hypergraphs
ICLR 2024
Rethinking Reconstruction-based Graph-Level Anomaly Detection: Limitations and a Simple Remedy
NeurIPS 2024
Tackling Prevalent Conditions in Unsupervised Combinatorial Optimization: Cardinality, Minimum, Covering, and More
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