Huiqi Deng

Orcid: 0009-0000-0754-0577

According to our database1, Huiqi Deng authored at least 24 papers between 2018 and 2024.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book 
In proceedings 
Article 
PhD thesis 
Dataset
Other 

Links

On csauthors.net:

Bibliography

2024
Interpretability of Neural Networks Based on Game-theoretic Interactions.
Mach. Intell. Res., August, 2024

Explainability for Large Language Models: A Survey.
ACM Trans. Intell. Syst. Technol., April, 2024

Unifying Fourteen Post-Hoc Attribution Methods With Taylor Interactions.
IEEE Trans. Pattern Anal. Mach. Intell., 2024

Memory Disagreement: A Pseudo-Labeling Measure from Training Dynamics for Semi-supervised Graph Learning.
Proceedings of the ACM on Web Conference 2024, 2024

Multi-Track Message Passing: Tackling Oversmoothing and Oversquashing in Graph Learning via Preventing Heterophily Mixing.
Proceedings of the Forty-first International Conference on Machine Learning, 2024

Mitigating Shortcuts in Language Models with Soft Label Encoding.
Proceedings of the 2024 Joint International Conference on Computational Linguistics, 2024

Explaining Generalization Power of a DNN Using Interactive Concepts.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

HAGO-Net: Hierarchical Geometric Massage Passing for Molecular Representation Learning.
Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023
Towards Attributions of Input Variables in a Coalition.
CoRR, 2023

Understanding and Unifying Fourteen Attribution Methods with Taylor Interactions.
CoRR, 2023

Bayesian Neural Networks Tend to Ignore Complex and Sensitive Concepts.
CoRR, 2023

Concept-Level Explanation for the Generalization of a DNN.
CoRR, 2023

Towards the Difficulty for a Deep Neural Network to Learn Concepts of Different Complexities.
Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Bayesian Neural Networks Avoid Encoding Complex and Perturbation-Sensitive Concepts.
Proceedings of the International Conference on Machine Learning, 2023

Defining and Quantifying the Emergence of Sparse Concepts in DNNs.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
Discovering and Explaining the Representation Bottleneck of DNNS.
Proceedings of the Tenth International Conference on Learning Representations, 2022

2021
Discovering and Explaining the Representation Bottleneck of DNNs.
CoRR, 2021

Towards Axiomatic, Hierarchical, and Symbolic Explanation for Deep Models.
CoRR, 2021

Mutual Information Preserving Back-propagation: Learn to Invert for Faithful Attribution.
Proceedings of the KDD '21: The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2021

A Unified Taylor Framework for Revisiting Attribution Methods.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020
Invariant subspace learning for time series data based on dynamic time warping distance.
Pattern Recognit., 2020

2019
UA-CRNN: Uncertainty-Aware Convolutional Recurrent Neural Network for Mortality Risk Prediction.
Proceedings of the 28th ACM International Conference on Information and Knowledge Management, 2019

2018
Robust Shapelets Learning: Transform-Invariant Prototypes.
Proceedings of the Pattern Recognition and Computer Vision - First Chinese Conference, 2018

A Hybrid Residual Network and Long Short-Term Memory Method for Peptic Ulcer Bleeding Mortality Prediction.
Proceedings of the AMIA 2018, 2018


  Loading...