Concept-wise granular computing for explainable artificial intelligence
Tóm tắt
Artificial neural networks offer great classification performances, but their internal model works as a black box. This can prevent their outcomes to be employed in real-world decision-making processes, e.g., in smart manufacturing. To address this issue, the neural network should provide human-comprehensible explanations for their outcomes. This can be achieved by exploiting domain concepts and measuring their importance for the classification. To this aim, we implement an information granulation process via a neural network specifically trained to represent data instances featuring the same (different) concept’s item close to (far away from) each other. By combining the representations for each concept, we obtain the so-called conceptual space embedding. The classification is obtained by processing it via a neural network classifier. The conceptual space embedding (i) organizes the data instances according to their concepts-wise proximity, resulting in a very informative data representation; this translates into greater classification accuracy if compared to a concept-wise approach from the state-of-the-art; and (ii) encodes each concept in one of its parts; this enables the measurement of the importance of one concept by manipulating the corresponding part of the conceptual space embedding. The proposed approach has been tested with real-world data from smart manufacturing.
Tài liệu tham khảo
Adadi A, Berrada M (2018) Peeking inside the black-box: a survey on explainable artificial intelligence (xai). IEEE Access 6:52,138-52,160
Afchar D, Guigue V, Hennequin R (2021) Towards rigorous interpretations: a formalisation of feature attribution. In: International Conference on Machine Learning, PMLR, pp 76–86
Ahmed I, Jeon G, Piccialli F (2022) From artificial intelligence to explainable artificial intelligence in industry 4.0: a survey on what, how, and where. IEEE Trans Indus Inform 18(8):5031–5042
Alfeo AL, Cimino MGC, Egidi S, et al (2017) Stigmergy-based modeling to discover urban activity patterns from positioning data. In: International Conference on Social Computing, Behavioral-Cultural Modeling and Prediction and Behavior Representation in Modeling and Simulation, Springer, pp 292–301
Alfeo AL, Cimino MG, Manco G et al (2020) Using an autoencoder in the design of an anomaly detector for smart manufacturing. Pattern Recognit Lett 136:272–278
Alfeo AL, Cimino MG, Vaglini G (2022a) Degradation stage classification via interpretable feature learning. J Manuf Syst 62:972–983
Alfeo AL, Cimino MGC, et al (2022b) Automatic feature extraction for bearings’ degradation assessment using minimally pre-processed time series and multi-modal feature learning. In: Proceedings of the 3rd International Conference on Innovative Intelligent Industrial Production and Logistics (IN4PL 2022)
Apicella A, Isgrò F, Prevete R et al (2020) Middle-level features for the explanation of classification systems by sparse dictionary methods. Int J Neural Syst 30(08):2050,040
Basu I, Maji S (2022) Multicollinearity correction and combined feature effect in shapley values. In: Australasian Joint Conference on Artificial Intelligence, Springer, pp 79–90
Bau D, Zhu JY, Strobelt H et al (2020) Understanding the role of individual units in a deep neural network. Proceedings of the National Academy of Sciences 117(48):30,071-30,078
Bengio Y, Courville A, Vincent P (2013) Representation learning: a review and new perspectives. IEEE Trans Pattern Anal Machine Intell 35(8):1798–1828
Chen Z, Bei Y, Rudin C (2020) Concept whitening for interpretable image recognition. Nat Machine Intell 2(12):772–782
Confalonieri R, Weyde T, Besold TR et al (2021) Using ontologies to enhance human understandability of global post-hoc explanations of black-box models. Artif Intell 296(103):471
Delaney E, Greene D, Keane MT (2021) Instance-based counterfactual explanations for time series classification. In: International Conference on Case-Based Reasoning, Springer, pp 32–47
Díaz-Rodríguez N, Lamas A, Sanchez J et al (2022) Explainable neural-symbolic learning (x-nesyl) methodology to fuse deep learning representations with expert knowledge graphs: the monumai cultural heritage use case. Inf Fusion 79:58–83
Ghorbani A, Wexler J, Zou JY, et al (2019) Towards automatic concept-based explanations. Adv Neural Inf Process Syst 32
Hitzler P, Sarker M (2022) Human-centered concept explanations for neural networks. Neuro-Symbolic Artif Intell: The State of the Art 342(337):2
Hu H, Pang L, Tian D et al (2014) Perception granular computing in visual haze-free task. Expert Syst Appl 41(6):2729–2741
İç YT, Yurdakul M (2021) Development of a new trapezoidal fuzzy ahp-topsis hybrid approach for manufacturing firm performance measurement. Granul Computing 6(4):915–929
Kazhdan D, Dimanov B, Terre HA, et al (2021) Is disentanglement all you need? Comparing concept-based & disentanglement approaches. arXiv preprint arXiv:2104.06917
Kim B, Wattenberg M, Gilmer J, et al (2018) Interpretability beyond feature attribution: quantitative testing with concept activation vectors (tcav). In: International Conference on Machine Learning, PMLR, pp 2668–2677
Koh PW, Nguyen T, Tang YS, et al (2020) Concept bottleneck models. In: International Conference on Machine Learning, PMLR, pp 5338–5348
Lake BM, Salakhutdinov R, Tenenbaum JB (2015) Human-level concept learning through probabilistic program induction. Science 350(6266):1332–1338
Lucieri A, Bajwa MN, Dengel A, et al (2020) Explaining ai-based decision support systems using concept localization maps. In: International Conference on Neural Information Processing, Springer, pp 185–193
Lundberg SM, Lee SI (2017) A unified approach to interpreting model predictions. Adv Neural Infor Process Syst 30
Miller T (2019) Explanation in artificial intelligence: insights from the social sciences. Artif Intell 267:1–38
Pedrycz W (1998) Conditional fuzzy clustering in the design of radial basis function neural networks. IEEE Trans Neural Netw 9(4):601–612
Qi J, Wei L, Wan Q (2019) Multi-level granularity in formal concept analysis. Granul Computing 4(3):351–362
Salehi S, Selamat A, Fujita H (2015) Systematic mapping study on granular computing. Knowl-Based Syst 80:78–97
Song M, Wang Y (2016) A study of granular computing in the agenda of growth of artificial neural networks. Granul Computing 1(4):247–257
Stursa D, Dolezel P (2019) Comparison of relu and linear saturated activation functions in neural network for universal approximation. In: 2019 22nd International Conference on Process Control (PC19), IEEE, pp 146–151
van der Waa J, Nieuwburg E, Cremers A et al (2021) Evaluating xai: a comparison of rule-based and example-based explanations. Artif Intell 291(103):404
van Zelst SJ, Mannhardt F, de Leoni M et al (2021) Event abstraction in process mining: literature review and taxonomy. Granul Computing 6(3):719–736
Wang X, Han X, Huang W, et al (2019) Multi-similarity loss with general pair weighting for deep metric learning. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 5022–5030
Zhou B, Bau D, Oliva A et al (2018) Interpreting deep visual representations via network dissection. IEEE Trans Pattern Anal Machine Intell 41(9):2131–2145
Zhou B, Khosla A, Lapedriza À, et al (2015) Object detectors emerge in deep scene cnns. In: Proceedings of the 3rd International Conference on Learning Representations (ICLR)