Cover Image

The Interaction Bottleneck of Deep Neural Networks: Discovery, Proof, and Modulation

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Deng, Huiqi, Ren, Qihan, Chen, Zhuofan, Cui, Zhenyuan, Shen, Wen, Zhang, Peng, Pei, Hongbin, Zhang, Quanshi
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Attribution Explanations for Deep Neural Networks: A Theoretical Perspective
by: Deng, Huiqi, et al.
Published: (2025)

Where We Have Arrived in Proving the Emergence of Sparse Symbolic Concepts in AI Models
by: Ren, Qihan, et al.
Published: (2023)

Towards Attributions of Input Variables in a Coalition
by: Zheng, Xinhao, et al.
Published: (2023)

Revisiting Generalization Power of a DNN in Terms of Symbolic Interactions
by: Cheng, Lei, et al.
Published: (2025)

Explaining Generalization Power of a DNN Using Interactive Concepts
by: Zhou, Huilin, et al.
Published: (2023)

Towards the Dynamics of a DNN Learning Symbolic Interactions
by: Ren, Qihan, et al.
Published: (2024)

Does a Neural Network Really Encode Symbolic Concepts?
by: Li, Mingjie, et al.
Published: (2023)

Probabilistic Abstract Interpretation on Neural Networks via Grids Approximation
by: Zhang, Zhuofan, et al.
Published: (2026)

Distribution and Clusters Approximations as Abstract Domains in Probabilistic Abstract Interpretation to Neural Network Analysis
by: Zhang, Zhuofan, et al.
Published: (2026)

Attributing Emergence in Million-Agent Systems
by: Tang, Ling, et al.
Published: (2026)

Technical Note: Defining and Quantifying AND-OR Interactions for Faithful and Concise Explanation of DNNs
by: Li, Mingjie, et al.
Published: (2023)

Understanding Generalization through Decision Pattern Shift
by: Deng, Huiqi, et al.
Published: (2026)

Towards the Resistance of Neural Network Watermarking to Fine-tuning
by: Tang, Ling, et al.
Published: (2025)

Reconciling Contradictory Views on the Effectiveness of SFT in LLMs: An Interaction Perspective
by: Zhang, Junpeng, et al.
Published: (2026)

Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability
by: Ren, Qihan, et al.
Published: (2026)

Layerwise Change of Knowledge in Neural Networks
by: Cheng, Xu, et al.
Published: (2024)

Topological Neural Networks: Mitigating the Bottlenecks of Graph Neural Networks via Higher-Order Interactions
by: Giusti, Lorenzo
Published: (2024)

Neural Interactive Proofs
by: Hammond, Lewis, et al.
Published: (2024)

Delayed Bottlenecking: Alleviating Forgetting in Pre-trained Graph Neural Networks
by: Zhao, Zhe, et al.
Published: (2024)

Two-Phase Dynamics of Interactions Explains the Starting Point of a DNN Learning Over-Fitted Features
by: Zhang, Junpeng, et al.
Published: (2024)

MemFly: On-the-Fly Memory Optimization via Information Bottleneck
by: Zhang, Zhenyuan, et al.
Published: (2026)

Evaluating the Correctness of Inference Patterns Used by LLMs for Judgment
by: Chen, Lu, et al.
Published: (2024)

Mitigating Translationese Bias in Multilingual LLM-as-a-Judge via Disentangled Information Bottleneck
by: Zhang, Hongbin, et al.
Published: (2026)

Editable Concept Bottleneck Models
by: Hu, Lijie, et al.
Published: (2024)

Discovering the Representation Bottleneck of Graph Neural Networks
by: Wu, Fang, et al.
Published: (2022)

Automatic Image Colorization with Convolutional Neural Networks and Generative Adversarial Networks
by: Qiu, Changyuan, et al.
Published: (2025)

Exploring Dynamic Properties of Backdoor Training Through Information Bottleneck
by: Liu, Xinyu, et al.
Published: (2025)

Interactive Training: Feedback-Driven Neural Network Optimization
by: Zhang, Wentao, et al.
Published: (2025)

SpecBound: Adaptive Bounded Self-Speculation with Layer-wise Confidence Calibration
by: Wen, Zhuofan, et al.
Published: (2026)

Learning Dynamics of Deep Learning -- Force Analysis of Deep Neural Networks
by: Ren, Yi
Published: (2025)

Randomness of Low-Layer Parameters Determines Confusing Samples in Terms of Interaction Representations of a DNN
by: Zhang, Junpeng, et al.
Published: (2025)

Proof-of-Use: Mitigating Tool-Call Hacking in Deep Research Agents
by: Ma, SHengjie, et al.
Published: (2025)

Proximity-Informed Calibration for Deep Neural Networks
by: Xiong, Miao, et al.
Published: (2023)

Thinking with Patterns: Breaking the Perceptual Bottleneck in Visual Planning via Pattern Induction
by: Jian, Yichang, et al.
Published: (2026)

Layer Embedding Deep Fusion Graph Neural Network
by: Xu, Taihua, et al.
Published: (2026)

MPCEval: A Benchmark for Multi-Party Conversation Generation
by: Zhang, Minxing, et al.
Published: (2026)

Bottleneck Tokens for Unified Multimodal Retrieval
by: Sun, Siyu, et al.
Published: (2026)

SF-GNN: Self Filter for Message Lossless Propagation in Deep Graph Neural Network
by: Zhu, Yushan, et al.
Published: (2024)

Defining and Extracting generalizable interaction primitives from DNNs
by: Chen, Lu, et al.
Published: (2024)

Deep Graph Neural Networks via Posteriori-Sampling-based Node-Adaptive Residual Module
by: Zhou, Jingbo, et al.
Published: (2023)