In this paper, we explore semantic clustering properties of deep reinforcement learning (DRL) to improve its interpretability and deepen our understanding of its internal semantic organization. In this context, semantic clustering refers to the ability of neural networks to cluster inputs based on their semantic similarity in the feature space. We propose a DRL architecture that incorporates a novel semantic clustering module that combines feature dimensionality reduction with online clustering. This module integrates seamlessly into the DRL training pipeline, addressing the instability of t-SNE and eliminating the need for extensive manual annotation inherent to prior semantic analysis methods. We experimentally validate the effectiveness of the proposed module and demonstrate its ability to reveal semantic clustering properties within DRL. Furthermore, we introduce new analytical methods based on these properties to provide insights into the hierarchical structure of policies and semantic organization within the feature space. Our code is available at https://github.com/ualiangzhang/semantic_rl.
Enhancing Topic Interpretability for Neural Topic Modeling through Topic-wise Contrastive Learning
Peking University(北京大学);Software Engineering Institution(软件工程研究院);Key Lab of High Confidence Software Technologies, Ministry of Education(高可信软件技术重点实验室(教育部));Center on Frontiers of Computing Studies(计算机前沿研究中心);National Engineering Research Center of Software Engineering(国家软件工程工程研究中心)
Don't Believe Everything You Read: Enhancing Summarization Interpretability through Automatic Identification of Hallucinations in Large Language Models
Enhancing Uncertainty Estimation and Interpretability via Bayesian Non-negative Decision Layer
National Key Laboratory of Radar Signal Processing, Xidian University(雷达信号处理国家重点实验室,西安电子科技大学);School of Mathematics and Statistics, Xi’an Jiaotong University(数学与统计学院,西安交通大学);McCombs School of Business, The University of Texas at Austin(商学院,德克萨斯大学奥斯汀分校)
Found in Translation: semantic approaches for enhancing AI interpretability in face verification
Université de Mons (UMONS)(蒙斯大学);Université Libre de Bruxelles (ULB)(布鲁塞尔自由大学);Laboratoire de Recherche de l'EPITA -- LRE(EPITA研究所(LRE));Univ Gustave Eiffel(古斯塔夫·埃菲尔大学);CNRS(法国国家科学研究中心);LIGM(信息与建模实验室)
SL-CBM: Enhancing Concept Bottleneck Models with Semantic Locality for Better Interpretability
Saarland University(萨尔大学);University of Chinese Academy of Sciences(中国科学院大学);Institute of Science Tokyo(东京科学大学);CISPA Helmholtz Center for Information Security(CISPA亥姆霍兹信息安全中心);Institute of Software, Chinese Academy of Science(中国科学院软件研究所)
When Fireflies Cluster; Enhancing Automatic Clustering via Centroid-Guided Firefly Optimization
Department of Computer Science, Faculty of Applied Sciences, University of Sri Jayewardenepura(Sri Lanka 瑞籍耶文纳普拉大学计算机科学系,应用科学学院);Faculty of Engineering and Natural Sciences,Tampere University(蒂帕雷大学工程与自然科学学院);Department of Mathematics and Statistics, University of Turku(图尔库大学数学与统计学系)
Enhancing Osteoporosis Detection: An Explainable Multi-Modal Learning Framework with Feature Fusion and Variable Clustering
School of Electrical and Computer Engineering, College of Engineering, University of Tehran(塔里班大学电气与计算机工程学院);Department of Epidemiology, Shiraz University of Medical Science(谢尔兹医学科学大学流行病学系);Department of Computer Science and Engineering, Sejong University(世宗大学计算机科学与工程系);School of Computing and Information Science, Anglia Ruskin University(安格利亚 Ruskin 大学计算与信息科学学院)
Towards Cohesion-Fairness Harmony: Contrastive Regularization in Individual Fair Graph Clustering
L3S Research Centre, Leibniz University Hannover(莱布尼茨汉诺威大学L3S研究中心);University of Kurdistan(库尔德斯坦大学);RI CODE, University of the Bundeswehr Munich(慕尼黑联邦国防军大学RI CODE)
CF-CAM: Cluster Filter Class Activation Mapping for Reliable Gradient-Based Interpretability
School of Physics, Mathematics, and Computing(物理、数学与计算学院);University of Western Australia(西澳大学);Hefei University of Technology(合肥工业大学);Department of Electrical and Computer Engineering(电气与计算机工程系);Stevens Institute of Technology(史蒂文斯理工学院)
Enabling Trustworthy Federated Learning in Industrial IoT: Bridging the Gap Between Interpretability and Robustness
Mepco Schlenk Engineering College(梅普科施伦克工程学院);Fordham University(福特汉姆大学);University of South Florida(南佛罗里达大学);Hung Yen University of Technology and Education(兴安工业大学);Royal Military College of Canada(加拿大皇家军事学院)
FG-CXR: A Radiologist-Aligned Gaze Dataset for Enhancing Interpretability in Chest X-Ray Report Generation
University of Arkansas(阿肯色大学);West Virginia University(西弗吉尼亚大学);University of Liverpool(利物浦大学);MD Anderson Cancer Center(MD安德森癌症中心);University of Houston(休斯顿大学)