Interpretable ML

ML: Machine Learning

Interpretable machine learning aims to make predictions understandable enough for people to inspect, challenge, and use, especially in high-stakes decisions and scientific discovery. Approaches include inherently transparent decision trees, rule sets, additive models, and symbolic formulas, as well as concept- and prototype-based models that connect predictions to human-readable ideas or examples. Other methods explain complex models after training with feature attributions, local surrogates, or analyses of internal representations, while newer work also builds in uncertainty, domain knowledge, and opportunities for human intervention. A central challenge is balancing predictive accuracy with explanations that are faithful, stable under changes in data, and meaningful to the people relying on them; evaluation increasingly tests these qualities rather than treating a plausible explanation as sufficient.

Latest papers

310 papers26 papers in the last four weeks, level with the four weeks before. 0.2% of all new papers.

MARS: A neurosymbolic approach for interpretable drug discovery
Oct 2, 2024Lauren Nicole DeLong, Yojana Gadiya, Paola Galdi +2Interpretable ML AI-Assisted Scientific Research
School of Informatics, University of Edinburgh, 10 Crichton St, Edinburgh, EH8 9AB, United Kingdom. · Cancer Research UK Scotland Institute, Switchback Road, Glasgow, G61 1BD, United Kingdom. · Enveda Therapeutics, 5700 Flatiron Parkway, Boulder, 80301, Colorado, United States of America.
Interpretable Clustering: A Survey
Sep 1, 2024Lianyu Hu, Mudi Jiang, Junjie Dong +2Clustering Interpretable ML
College of Information Science and Engineering, Henan University of Technology, China · School of Software, Dalian University of Technology, China · Xinchang Power Supply Company, State Grid Corporation of China, China
MambaCapsule: Towards Transparent Cardiac Disease Diagnosis with Electrocardiography Using Mamba Capsule Network
Jul 30, 2024Yinlong Xu, Zitai Kong, Yixuan Wu +5Interpretable ML Electrocardiogram Classification
State Key Laboratory of Transvascular Implantation Devices and TIDRI, Zhejiang University, Hangzhou, China · School of Public Health, Zhejiang University and Zhejiang Key Laboratory of Medical Imaging Artificial Intelligence, Hangzhu, China · State Key Laboratory of Transvascular Implantation Devices of The Second Affiliated Hospital and Liangzhu Laboratory, Zhejiang University, Hangzhou, China +3
Probabilistic Truly Unordered Rule Sets
Jan 18, 2024Lincen Yang, Matthijs van LeeuwenInterpretable ML Multiclass Classification
LIACS, Leiden University Niels Bohrweg 1, 2333 CA, Leiden, The Netherlands
Fast, Interpretable, and Deterministic Time Series Classification With a Bag-of-Receptive-Fields
Nov 29, 2023Francesco Spinnato, Riccardo Guidotti, Anna Monreale +1Time Series Classification Interpretable ML
Scuola Normale Superiore, Pisa, Italy · University of Pisa, Pisa, Italy · ISTI-CNR, Pisa, Italy
Topology-enhanced machine learning for speech signal processing
Nov 26, 2023Pingyao Feng, Qingrui Qu, Haiyu Zhang +4Interpretable ML Speech Processing
Department of Mathematics, Southern University of Science and Technology, Shenzhen, China. · Department of Mathematics, North Carolina State University, Raleigh, NC, USA. · School of Intelligence Science and Engineering, Harbin Institute of Technology (Shenzhen), Shenzhen, China. +1
Distributionally Robust Regularization of Sparse Integer Programming Trained Learning Models
Nov 3, 2023Sanjeeb Dash, Soumyadip Ghosh, Joao Goncalves +1Rule-Based Classification Interpretable ML
IBM Research, Yorktown Heights, NY 10598
Granular-ball computing: an efficient, robust, and interpretable adaptive multi-granularity representation and computation method
Apr 21, 2023Shuyin Xia, Guoyin Wang, Xinbo Gao +2Interpretable ML Adaptive Computation
Chongqing Key Laboratory of Computational Intelligence, Key Laboratory of Cyberspace Big Data Intelligent Security, Ministry of Education, and Key Laboratory of Big Data Intelligent Computing, Chongqing University of Posts and Telecommunications, 400065, Chongqing, China · College of Computer and Information Science, the National Center for Applied Mathematics in Chongqing, Chongqing Normal University, Chongqing 401331, China
Rule Extraction in Machine Learning: Chat Incremental Pattern Constructor
Jul 31, 2022Caleb Princewill NwokochaInterpretable ML Incremental Learning
Deep Learning for Individual Heterogeneity
Oct 28, 2020Max H. Farrell, Tengyuan Liang, Sanjog MisraInterpretable ML
Department of Economics, UC Santa Barbara · Booth School of Business, University of Chicago

Oct 2, 2024J/K move · Enter open · S save

MARS: A neurosymbolic approach for interpretable drug discovery

Lauren Nicole DeLong, Yojana Gadiya, Paola Galdi, Jacques D. Fleuriot+1

School of Informatics, University of Edinburgh, 10 Crichton St, Edinburgh, EH8 9AB, United Kingdom. · Cancer Research UK Scotland Institute, Switchback Road, Glasgow, G61 1BD, United Kingdom. · Enveda Therapeutics, 5700 Flatiron Parkway, Boulder, 80301, Colorado, United States of America.

Interpretable ML AI-Assisted Scientific Research Neuro-Symbolic Reasoning Shortcut Learning Drug Discovery

Open paper AskPDF arXiv

Background: Neurosymbolic (NeSy) artificial intelligence describes the combination of logic or rule-based techniques with neural networks. Compared to neural approaches, NeSy methods often possess enhanced interpretability, which is particularly promising for biomedical applications like drug discovery. However, no clear guidelines exist to assess the biological plausibility of model interpretations. Methods: To assess interpretability in the context of drug discovery, we devise a novel prediction task, called drug mechanism-of-action (MoA) deconvolution, with an associated, tailored knowledge graph (KG), MoA-net. We then develop the MoA Retrieval System (MARS), a NeSy approach for drug discovery which leverages logical rules with learned rule weights. Results: Using MARS' interpretable features alongside domain knowledge, we find that MARS and other NeSy approaches on KGs are susceptible to reasoning shortcuts, in which the prediction of true labels is driven by ``degree-bias'' rather than the domain-based rules. Subsequently, we demonstrate ways to identify and mitigate this. Thereafter, MARS achieves performance on par with current state-of-the-art models while producing model interpretations aligned with known MoAs. Conclusion: Through MARS, we showcase the novel task of computational MoA deconvolution. Our results emphasize the importance of using interpretable models, like NeSy ones, for applications in drug discovery. Specifically, by identifying and mitigating reasoning shortcuts, MARS MoA predictions which are biologically meaningful and, therefore, more reliable for downstream drug discovery research.