Longitudinal Distance: Towards Accountable Instance Attribution

Previous research in interpretable machine learning (IML) and explainable artificial intelligence (XAI) can be broadly categorized as either focusing on seeking interpretability in the agent’s model (i.e., IML) or focusing on the context of the user in addition to the model (i.e., XAI). The former can be categorized as feature or instance attribution. Exampleor sample-based methods such as those using or inspired by case-based reasoning (CBR) rely on various approaches to select instances that are not necessarily attributing instances responsible for an agent’s decision. Furthermore, existing approaches have focused on interpretability and explainability but fall short when it comes to accountability. Inspired in case-based reasoning principles, this paper introduces a pseudo-metric we call Longitudinal distance and its use to attribute instances to a neural network agent’s decision that can be potentially used to build accountable CBR agents.

[1]  Arvind Satyanarayan,et al.  The Building Blocks of Interpretability , 2018 .

[2]  Mariarosaria Taddeo,et al.  The ethics of algorithms: Mapping the debate , 2016, Big Data Soc..

[3]  Gintare Karolina Dziugaite,et al.  RelatIF: Identifying Explanatory Training Examples via Relative Influence , 2020, ArXiv.

[4]  Suresh Venkatasubramanian,et al.  Auditing black-box models for indirect influence , 2016, Knowledge and Information Systems.

[5]  Ankur Taly,et al.  Axiomatic Attribution for Deep Networks , 2017, ICML.

[6]  Jeanna Neefe Matthews,et al.  Toward algorithmic transparency and accountability , 2017, Commun. ACM.

[7]  Avanti Shrikumar,et al.  Learning Important Features Through Propagating Activation Differences , 2017, ICML.

[8]  Yair Zick,et al.  Axiomatic Characterization of Data-Driven Influence Measures for Classification , 2017, AAAI.

[9]  Amit Sharma,et al.  Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers , 2019, ArXiv.

[10]  Alexander Binder,et al.  On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation , 2015, PloS one.

[11]  Martin Wattenberg,et al.  Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV) , 2017, ICML.

[12]  Chunyan Miao,et al.  HYDRA: Hypergradient Data Relevance Analysis for Interpreting Deep Neural Networks , 2021, AAAI.

[13]  Alan Fern,et al.  Learning Finite State Representations of Recurrent Policy Networks , 2018, ICLR.

[14]  José M. F. Moura,et al.  Building Human-Machine Trust via Interpretability , 2019, AAAI.

[15]  Tommi S. Jaakkola,et al.  Towards Robust Interpretability with Self-Explaining Neural Networks , 2018, NeurIPS.

[16]  Mark T. Keane,et al.  Twin-Systems to Explain Artificial Neural Networks using Case-Based Reasoning: Comparative Tests of Feature-Weighting Methods in ANN-CBR Twins for XAI , 2019, IJCAI.

[17]  Oluwasanmi Koyejo,et al.  Interpreting Black Box Predictions using Fisher Kernels , 2018, AISTATS.

[18]  Ke Xu,et al.  Towards Ground Truth Explainability on Tabular Data , 2020, ArXiv.

[19]  Pradeep Ravikumar,et al.  Representer Point Selection for Explaining Deep Neural Networks , 2018, NeurIPS.

[20]  Xin Man,et al.  The Best Way to Select Features? Comparing MDA, LIME, and SHAP , 2020, The Journal of Financial Data Science.

[21]  Been Kim,et al.  Sanity Checks for Saliency Maps , 2018, NeurIPS.

[22]  Chris Russell,et al.  Explaining Explanations in AI , 2018, FAT.

[23]  J. Reidenberg,et al.  Accountable Algorithms , 2016 .

[24]  Percy Liang,et al.  Understanding Black-box Predictions via Influence Functions , 2017, ICML.

[25]  Scott Lundberg,et al.  A Unified Approach to Interpreting Model Predictions , 2017, NIPS.

[26]  Carlos Guestrin,et al.  "Why Should I Trust You?": Explaining the Predictions of Any Classifier , 2016, ArXiv.

[27]  Michael McCloskey,et al.  Catastrophic Interference in Connectionist Networks: The Sequential Learning Problem , 1989 .

[28]  Dumitru Erhan,et al.  A Benchmark for Interpretability Methods in Deep Neural Networks , 2018, NeurIPS.

[29]  Riccardo Guidotti,et al.  Evaluating local explanation methods on ground truth , 2021, Artif. Intell..

[30]  Prateek Goel,et al.  Data Representing Ground-Truth Explanations to Evaluate XAI Methods , 2020, ArXiv.