paper-with-me

홈 › Papers

Identifying Information-Transfer Nodes in a Recurrent Neural Network Reveals Dynamic Representations

2025-09-29 · Arend Hintze, Asadullah Najam, Jory Schossau arxiv

Understanding the internal dynamics of Recurrent Neural Networks (RNNs) is crucial for advancing their interpretability and improving their design. This study introduces an innovative information-theoretic method to identify and analyze information-transfer nodes within RNNs, which we refer to as \textit{information relays}. By quantifying the mutual information between input and output vectors across nodes, our approach pinpoints critical pathways through which information flows during network operations. We apply this methodology to both synthetic and real-world time series classification tasks, employing various RNN architectures, including Long Short-Term Memory (LSTM) networks and Gated Recurrent Units (GRUs). Our results reveal distinct patterns of information relay across different architectures, offering insights into how information is processed and maintained over time. Additionally, we conduct node knockout experiments to assess the functional importance of identified nodes, significantly contributing to explainable artificial intelligence by elucidating how specific nodes influence overall network behavior. This study not only enhances our understanding of the complex mechanisms driving RNNs but also provides a valuable tool for designing more robust and interpretable neural networks.

📄 PDF Abstract BibTeX arXiv:2510.01271

Code (0)

등록된 구현이 없습니다.

Tasks

Time Series Classification

Similar Papers 제목 키워드 기반

Identifying negative language transfer in learner errors using POS information

2021-04-01 · EACL (BEA) 2021 4 · Leticia Farias Wanderley, Carrie Demmans Epp

A common mistake made by language learners is the misguided usage of first language rules when communicating in another language. In this paper, n-gram and recurrent neural network language models are used to represent l…

POS

Recurrent Knowledge Identification and Fusion for Language Model Continual Learning

2025-02-22 · Yujie Feng, Xujia Wang, Zexin Lu, Shenghong Fu 외

Continual learning (CL) is crucial for deploying large language models (LLMs) in dynamic real-world environments without costly retraining. While recent model ensemble and model merging methods guided by parameter import…

Continual LearningLanguage ModelingLanguage ModellingTransfer Learning

A Versatile Hub Model For Efficient Information Propagation And Feature Selection

2023-07-05 · Zhaoze Wang, Junsong Wang

Hub structure, characterized by a few highly interconnected nodes surrounded by a larger number of nodes with fewer connections, is a prominent topological feature of biological brains, contributing to efficient informat…

feature selection

Can GNNs Learn Link Heuristics? A Concise Review and Evaluation of Link Prediction Methods

2024-11-22 · Shuming Liang, Yu Ding, Zhidong Li, Bin Liang 외

This paper explores the ability of Graph Neural Networks (GNNs) in learning various forms of information for link prediction, alongside a brief review of existing link prediction methods. Our analysis reveals that GNNs c…

AttributeLink PredictionPrediction

Online Dynamic Network Embedding

2020-06-30 · Haiwei Huang, Jinlong Li, Huimin He, Huanhuan Chen

Network embedding is a very important method for network data. However, most of the algorithms can only deal with static networks. In this paper, we propose an algorithm Recurrent Neural Network Embedding (RNNE) to deal …

Network Embedding