Quanshi Zhang

IEEE Trans. Mob. Comput., July, 2024

Interpretable Rotation-Equivariant Quaternion Neural Networks for 3D Point Cloud Processing.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., May, 2024

An Introspective Data Augmentation Method for Training Math Word Problem Solvers.

[BibT_eX]

[DOI]

IEEE ACM Trans. Audio Speech Lang. Process., 2024

Unifying Fourteen Post-Hoc Attribution Methods With Taylor Interactions.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., 2024

Alignment Between the Decision-Making Logic of LLMs and Human Cognition: A Case Study on Legal LLMs.

[BibT_eX]

[DOI]

CoRR, 2024

Disentangling Regional Primitives for Image Generation.

[BibT_eX]

[DOI]

CoRR, 2024

Towards the Dynamics of a DNN Learning Symbolic Interactions.

[BibT_eX]

[DOI]

CoRR, 2024

Quantifying In-Context Reasoning Effects and Memorization Effects in LLMs.

[BibT_eX]

[DOI]

CoRR, 2024

Two-Phase Dynamics of Interactions Explains the Starting Point of a DNN Learning Over-Fitted Features.

[BibT_eX]

[DOI]

CoRR, 2024

Layerwise Change of Knowledge in Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the Forty-first International Conference on Machine Learning, 2024

Where We Have Arrived in Proving the Emergence of Sparse Interaction Primitives in DNNs.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Defining and extracting generalizable interaction primitives from DNNs.

[BibT_eX]

[DOI]

Proceedings of the Twelfth International Conference on Learning Representations, 2024

Identifying Semantic Induction Heads to Understand In-Context Learning.

[BibT_eX]

[DOI]

Proceedings of the Findings of the Association for Computational Linguistics, 2024

Explaining Generalization Power of a DNN Using Interactive Concepts.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

Batch Normalization Is Blind to the First and Second Derivatives of the Loss.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

Clarifying the Behavior and the Difficulty of Adversarial Training.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Eighth AAAI Conference on Artificial Intelligence, 2024

2023

Quantifying the Knowledge in a DNN to Explain Knowledge Distillation for Classification.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., April, 2023

Explaining How a Neural Network Play the Go Game and Let People Learn.

[BibT_eX]

[DOI]

CoRR, 2023

Towards Attributions of Input Variables in a Coalition.

[BibT_eX]

[DOI]

Xinhao Zheng

Huiqi Deng

CoRR, 2023

Where We Have Arrived in Proving the Emergence of Sparse Symbolic Concepts in AI Models.

[BibT_eX]

[DOI]

CoRR, 2023

Technical Note: Defining and Quantifying AND-OR Interactions for Faithful and Concise Explanation of DNNs.

[BibT_eX]

[DOI]

CoRR, 2023

Can the Inference Logic of Large Language Models be Disentangled into Symbolic Concepts?

[BibT_eX]

[DOI]

CoRR, 2023

Understanding and Unifying Fourteen Attribution Methods with Taylor Interactions.

[BibT_eX]

[DOI]

CoRR, 2023

Bayesian Neural Networks Tend to Ignore Complex and Sensitive Concepts.

[BibT_eX]

[DOI]

CoRR, 2023

Concept-Level Explanation for the Generalization of a DNN.

[BibT_eX]

[DOI]

CoRR, 2023

Does a Neural Network Really Encode Symbolic Concept?

[BibT_eX]

[DOI]

CoRR, 2023

Network Transplanting for the Functionally Modular Architecture.

[BibT_eX]

[DOI]

Proceedings of the Pattern Recognition and Computer Vision - 6th Chinese Conference, 2023

Towards the Difficulty for a Deep Neural Network to Learn Concepts of Different Complexities.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Defects of Convolutional Decoder Networks in Frequency Representation.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

Bayesian Neural Networks Avoid Encoding Complex and Perturbation-Sensitive Concepts.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

Does a Neural Network Really Encode Symbolic Concepts?

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

HarsanyiNet: Computing Accurate Shapley Values in a Single Forward Propagation.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2023

Can We Faithfully Represent Absence States to Compute Shapley Values on a DNN?

[BibT_eX]

[DOI]

Proceedings of the Eleventh International Conference on Learning Representations, 2023

Defining and Quantifying the Emergence of Sparse Concepts in DNNs.

[BibT_eX]

[DOI]

Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022

Rapid detection and recognition of whole brain activity in a freely behaving Caenorhabditis elegans.

[BibT_eX]

[DOI]

PLoS Comput. Biol., October, 2022

Proving Common Mechanisms Shared by Twelve Methods of Boosting Adversarial Transferability.

[BibT_eX]

[DOI]

CoRR, 2022

Batch Normalization Is Blind to the First and Second Derivatives of the Loss.

[BibT_eX]

[DOI]

CoRR, 2022

Why Adversarial Training of ReLU Networks Is Difficult?

[BibT_eX]

[DOI]

CoRR, 2022

RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL.

[BibT_eX]

[DOI]

CoRR, 2022

Quantification and Analysis of Layer-wise and Pixel-wise Information Discarding.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

Towards Theoretical Analysis of Transformation Complexity of ReLU DNNs.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Machine Learning, 2022

Discovering and Explaining the Representation Bottleneck of DNNS.

[BibT_eX]

[DOI]

Proceedings of the Tenth International Conference on Learning Representations, 2022

RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL.

[BibT_eX]

[DOI]

Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, 2022

Exploring Image Regions Not Well Encoded by an INN.

[BibT_eX]

[DOI]

Proceedings of the International Conference on Artificial Intelligence and Statistics, 2022

Interpretable Generative Adversarial Networks.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence, 2022

2021

Interpretable CNNs for Object Classification.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., 2021

Extraction of an Explanatory Graph to Interpret a CNN.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., 2021

Mining Interpretable AOG Representations From Convolutional Networks via Active Question Answering.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., 2021

Trap of Feature Diversity in the Learning of MLPs.

[BibT_eX]

[DOI]

CoRR, 2021

Discovering and Explaining the Representation Bottleneck of DNNs.

[BibT_eX]

[DOI]

CoRR, 2021

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

[BibT_eX]

[DOI]

CoRR, 2021

A Hypothesis for the Aesthetic Appreciation in Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2021

Proceedings of ICML 2021 Workshop on Theoretic Foundation, Criticism, and Application Trend of Explainable AI.

[BibT_eX]

[DOI]

CoRR, 2021

A Game-Theoretic Taxonomy of Visual Concepts in DNNs.

[BibT_eX]

[DOI]

CoRR, 2021

Learning Baseline Values for Shapley Values.

[BibT_eX]

[DOI]

CoRR, 2021

Game-theoretic Understanding of Adversarially Learned Features.

[BibT_eX]

[DOI]

CoRR, 2021

Interpreting Representation Quality of DNNs for 3D Point Cloud Processing.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Towards a Unified Game-Theoretic View of Adversarial Perturbations and Robustness.

[BibT_eX]

[DOI]

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Visualizing the Emergence of Intermediate Visual Patterns in DNNs.

[BibT_eX]

[DOI]

Shaobo Wang

Proceedings of the Advances in Neural Information Processing Systems 34: Annual Conference on Neural Information Processing Systems 2021, 2021

Interpretable Compositional Convolutional Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, 2021

Interpreting and Disentangling Feature Components of Various Complexity from DNNs.

[BibT_eX]

[DOI]

Proceedings of the 38th International Conference on Machine Learning, 2021

Interpreting and Boosting Dropout from a Game-Theoretic View.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

A Unified Approach to Interpreting and Boosting Adversarial Transferability.

[BibT_eX]

[DOI]

Proceedings of the 9th International Conference on Learning Representations, 2021

Interpreting Attributions and Interactions of Adversarial Attacks.

[BibT_eX]

[DOI]

Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Verifiability and Predictability: Interpreting Utilities of Network Architectures for Point Cloud Processing.

[BibT_eX]

[DOI]

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2021

Building Interpretable Interaction Trees for Deep NLP Models.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

Interpreting Multivariate Shapley Interactions in DNNs.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020

Game-Theoretic Interactions of Different Orders.

[BibT_eX]

[DOI]

CoRR, 2020

Interpreting Multivariate Interactions in DNNs.

[BibT_eX]

[DOI]

CoRR, 2020

Achieving Adversarial Robustness via Sparsity.

[BibT_eX]

[DOI]

CoRR, 2020

Interpreting Hierarchical Linguistic Interactions in DNNs.

[BibT_eX]

[DOI]

CoRR, 2020

Rotation-Equivariant Neural Networks for Privacy Protection.

[BibT_eX]

[DOI]

CoRR, 2020

Deep Quaternion Features for Privacy Protection.

[BibT_eX]

[DOI]

CoRR, 2020

Interpretable Complex-Valued Neural Networks for Privacy Protection.

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Learning Representations, 2020

Knowledge Consistency between Neural Networks and Beyond.

[BibT_eX]

[DOI]

Proceedings of the 8th International Conference on Learning Representations, 2020

3D-Rotation-Equivariant Quaternion Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the Computer Vision - ECCV 2020, 2020

Explaining Knowledge Distillation by Quantifying the Knowledge.

[BibT_eX]

[DOI]

Proceedings of the 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020

2019

Visual graph mining for graph matching.

[BibT_eX]

[DOI]

Comput. Vis. Image Underst., 2019

Preventing Information Leakage with Neural Architecture Search.

[BibT_eX]

[DOI]

CoRR, 2019

Utility Analysis of Network Architectures for 3D Point Cloud Processing.

[BibT_eX]

[DOI]

CoRR, 2019

Towards a Unified Evaluation of Explanation Methods without Ground Truth.

[BibT_eX]

[DOI]

CoRR, 2019

Knowledge Isomorphism between Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2019

Quantifying Layerwise Information Discarding of Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2019

Complex-Valued Neural Networks for Privacy Protection.

[BibT_eX]

[DOI]

CoRR, 2019

Proceedings of AAAI 2019 Workshop on Network Interpretability for Deep Learning.

[BibT_eX]

[DOI]

Lixin Fan

Bolei Zhou

CoRR, 2019

Unsupervised Learning of Neural Networks to Explain Neural Networks (extended abstract).

[BibT_eX]

[DOI]

Yu Yang

CoRR, 2019

Network Transplanting (extended abstract).

[BibT_eX]

[DOI]

CoRR, 2019

Interpretable CNNs.

[BibT_eX]

[DOI]

CoRR, 2019

Explaining AlphaGo: Interpreting Contextual Effects in Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2019

Reports of the Workshops Held at the 2019 AAAI Conference on Artificial Intelligence.

[BibT_eX]

[DOI]

AI Mag., 2019

Towards a Deep and Unified Understanding of Deep Neural Models in NLP.

[BibT_eX]

[DOI]

Proceedings of the 36th International Conference on Machine Learning, 2019

Explaining Neural Networks Semantically and Quantitatively.

[BibT_eX]

[DOI]

Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

Interpreting CNNs via Decision Trees.

[BibT_eX]

[DOI]

Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2019

2018

Visual interpretability for deep learning: a survey.

[BibT_eX]

[DOI]

Frontiers Inf. Technol. Electron. Eng., 2018

Mining deep And-Or object structures via cost-sensitive question-answer-based active annotations.

[BibT_eX]

[DOI]

Comput. Vis. Image Underst., 2018

Explanatory Graphs for CNNs.

[BibT_eX]

[DOI]

CoRR, 2018

Mining Interpretable AOG Representations from Convolutional Networks via Active Question Answering.

[BibT_eX]

[DOI]

CoRR, 2018

Unsupervised Learning of Neural Networks to Explain Neural Networks.

[BibT_eX]

[DOI]

CoRR, 2018

Network Transplanting.

[BibT_eX]

[DOI]

CoRR, 2018

Interpreting CNNs via Decision Trees.

[BibT_eX]

[DOI]

CoRR, 2018

Interpretable Convolutional Neural Networks.

[BibT_eX]

[DOI]

Proceedings of the 2018 IEEE Conference on Computer Vision and Pattern Recognition, 2018

Examining CNN Representations With Respect to Dataset Bias.

[BibT_eX]

[DOI]

Wenguan Wang

Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018

Interpreting CNN Knowledge via an Explanatory Graph.

[BibT_eX]

[DOI]

Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence, 2018

2017

Prediction and Simulation of Human Mobility Following Natural Disasters.

[BibT_eX]

[DOI]

ACM Trans. Intell. Syst. Technol., 2017

Visual Graph Mining.

[BibT_eX]

[DOI]

Xuan Song

Ryosuke Shibasaki

CoRR, 2017

A Cost-Sensitive Visual Question-Answer Framework for Mining a Deep And-OR Object Semantics from Web Images.

[BibT_eX]

[DOI]

CoRR, 2017

Interactively Transferring CNN Patterns for Part Localization.

[BibT_eX]

[DOI]

CoRR, 2017

Mining Object Parts from CNNs via Active Question-Answering.

[BibT_eX]

[DOI]

Proceedings of the 2017 IEEE Conference on Computer Vision and Pattern Recognition, 2017

Growing Interpretable Part Graphs on ConvNets via Multi-Shot Learning.

[BibT_eX]

[DOI]

Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, 2017

2016

Object Discovery: Soft Attributed Graph Mining.

[BibT_eX]

[DOI]

IEEE Trans. Pattern Anal. Mach. Intell., 2016

Multi-Shot Mining Semantic Part Concepts in CNNs.

[BibT_eX]

[DOI]

CoRR, 2016

2015

From RGB-D Images to RGB Images: Single Labeling for Mining Visual Models.

[BibT_eX]

[DOI]

ACM Trans. Intell. Syst. Technol., 2015

Mining And-Or Graphs for Graph Matching and Object Discovery.

[BibT_eX]

[DOI]