Huiqi Deng
11 papers · 2021–2025 · 6 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
π Interdisciplinary Bridge π§ Keyword Pioneer π Renaissance Researcher (6) πΊοΈ Taxonomy Completionist (20) π£ Hot Topic Early Bird
π
Conference Polyglot
(6)
π
Cross-Pollinator
(13)
π
Grand Slam
π
Century Club
(11)
π₯
Unstoppable
(5)
Conferences
ICML (4)
AAAI (3)
COLING (1)
CVPR (1)
ICLR (1)
NIPS (1)
Top co-authors
Keywords
neural network
(3)
deep neural network
(3)
neural network interpretability
(2)
symbolic reasoning
(1)
natural language understanding
(1)
geometric graph neural network
(1)
feature importance
(1)
neural network theory
(1)
concept learning
(1)
and-or graph
(1)
graphical model
(1)
model explanation
(1)
out-of-distribution generalization
(1)
spurious correlation
(1)
deep learning theory
(1)
bayesian neural network
(1)
soft label
(1)
property prediction
(1)
molecular property prediction
(1)
variational inference
(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
HAGO-Net: Hierarchical Geometric Message Passing for Molecular Representation Learning
AAAI 2024
Multi-Track Message Passing: Tackling Oversmoothing and Oversquashing in Graph Learning via Preventing Heterophily Mixing
ICML 2024
Explaining Generalization Power of a DNN Using Interactive Concepts
AAAI 2024
Mitigating Shortcuts in Language Models with Soft Label Encoding
COLING 2024
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
NIPS 2023
Bayesian Neural Networks Avoid Encoding Complex and Perturbation-Sensitive Concepts
ICML 2023
DISCOVERING AND EXPLAINING THE REPRESENTATION BOTTLENECK OF DNNS
ICLR 2022
A Unified Taylor Framework for Revisiting Attribution Methods
AAAI 2021