Forward Composition Propagation for Explainable Neural Reasoning
Not on the map. Why?
Abstract (arXiv)
This paper proposes an algorithm called Forward Composition Propagation (FCP) to explain the predictions of feed-forward neural networks operating on structured classification problems. In the proposed FCP algorithm, each neuron is described by a composition vector indicating the role of each problem feature in that neuron. Composition vectors are initialized using a given input instance and subsequently propagated through the whole network until reaching the output layer. The sign of each composition value indicates whether the corresponding feature excites or inhibits the neuron, while the absolute value quantifies its impact. The FCP algorithm is executed on a post-hoc basis, i.e., once the learning process is completed. Aiming to illustrate the FCP algorithm, this paper develops a case study concerning bias detection in a fairness problem in which the ground truth is known. The simulation results show that the composition values closely align with the expected behavior of protected features. The source code and supplementary material for this paper are available at https://github.com/igraugar/fcp.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 49 references that are in the map. First posted on arXiv 23 Dec 2021.
Builds on
27 of 49 references.
References · 27
- 2014Adam: A Method for Stochastic Optimizationcited by 37,240
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,733
- 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
- 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,070
- 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
- 2013Visualizing and Understanding Convolutional Networkscited by 2,290
- 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
- 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
- 2017Learning Important Features Through Propagating Activation Differencescited by 1,458
- 2014Striving for Simplicity: The All Convolutional Netcited by 990
- 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 708
- 2014OpenML: networked science in machine learningcited by 526
15 more
- 2015Evaluating the visualization of what a Deep Neural Network has learnedcited by 419
- 2018Deep Learning for Generic Object Detection: A Surveycited by 392
- 2018All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneouslycited by 373
- 2016RETAIN: An Interpretable Predictive Model for Healthcare using Reverse Time Attention Mechanismcited by 349
- 2018AI Fairness 360: An Extensible Toolkit for Detecting, Understanding, and Mitigating Unwanted Algorithmic Biascited by 319
- 2015Explaining NonLinear Classification Decisions with Deep Taylor Decompositioncited by 250
- 2017Real Time Image Saliency for Black Box Classifierscited by 246
- 2017Distilling a Neural Network Into a Soft Decision Treecited by 236
- 2018A comparative study of fairness-enhancing interventions in machine learningcited by 208
- 2020Compositional Explanations of Neuronscited by 172
- 2017Explaining Recurrent Neural Network Predictions in Sentiment Analysiscited by 88
- 2020Do the Machine Learning Models on a Crowd Sourced Platform Exhibit Bias? An Empirical Study on Model Fairnesscited by 52
- 2017Interpretability via Model Extractioncited by 40
- 2016Rule Extraction Algorithm for Deep Neural Networks: A Reviewcited by 22
- 2021A fuzzy-rough uncertainty measure to discover bias encoded explicitly or implicitly in features of structured pattern classification datasetscited by 5
Built on by
Not cited yet.