Huiqi Deng
11 papers · 2021–2025 · 6 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 ↓+4 more ↓ Show less ↑
π Interdisciplinary Bridge Β· Silver πΊοΈ Taxonomy Completionist (21) π£ Hot Topic Early Bird π Conference Polyglot Β· Silver π Grand Slam
π
Renaissance Researcher
(5)
π₯
Unstoppable Β· Bronze
π
Century Club Β· Bronze
ποΈ
Keyword Collector
(63)
Top co-authors
Research topics
Machine Learning
(10)
Deep Learning
(8)
Artificial Intelligence
(5)
Core AI
(5)
Core Methods
(5)
Optimization & Theory Β· Machine Learning
(5)
Architectures
(4)
Learning Types
(3)
Optimization & Theory Β· Deep Learning
(2)
Computer Vision
(1)
Healthcare & Medicine
(1)
Interdisciplinary
(1)
Natural Language Processing
(1)
Analysis
(1)
Application Areas
(1)
Keywords
neural network
(4)
deep neural network
(3)
neural network interpretability
(2)
feature learning
(1)
deep learning theory
(1)
feature importance
(1)
symbolic reasoning
(1)
loss function
(1)
out-of-distribution generalization
(1)
neural network theory
(1)
message passing
(1)
concept learning
(1)
and-or graph
(1)
graphical model
(1)
spatial pattern
(1)
natural language understanding
(1)
variational inference
(1)
geometric graph neural network
(1)
spurious correlation
(1)
learning theory
(1)
Papers
Non-Stationary Predictions May Be More Informative: Exploring Pseudo-Labels with a Two-Phase Pattern of Training Dynamics
ICML 2025
Towards Attributions of Input Variables in a Coalition
ICML 2025
Explaining Generalization Power of a DNN Using Interactive Concepts
AAAI 2024
HAGO-Net: Hierarchical Geometric Message Passing for Molecular Representation Learning
AAAI 2024
Mitigating Shortcuts in Language Models with Soft Label Encoding
COLING 2024
Multi-Track Message Passing: Tackling Oversmoothing and Oversquashing in Graph Learning via Preventing Heterophily Mixing
ICML 2024
Bayesian Neural Networks Avoid Encoding Complex and Perturbation-Sensitive Concepts
ICML 2023
Defining and Quantifying the Emergence of Sparse Concepts in DNNs
CVPR 2023
Towards the Difficulty for a Deep Neural Network to Learn Concepts of Different Complexities
NeurIPS 2023
DISCOVERING AND EXPLAINING THE REPRESENTATION BOTTLENECK OF DNNS
ICLR 2022
A Unified Taylor Framework for Revisiting Attribution Methods
AAAI 2021