Greybox XAI: A Neural-Symbolic learning framework to produce interpretable predictions for image classification

Preece, 2018 Gunning, 2017 Goodman, 2017, European union regulations on algorithmic decision-making and a “right to explanation”, AI Mag., 38, 50 R. Caruana, Y. Lou, J. Gehrke, P. Koch, M. Sturm, N. Elhadad, Intelligible Models for HealthCare: Predicting Pneumonia Risk and Hospital 30-day Readmission, in: Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD ’15, 2015, pp. 1721–1730. Zhu, 2018, Explainable AI for designers: A human-centered perspective on mixed-initiative co-creation, 1 Arrieta, 2020, Explainable artificial intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI, Inf. Fusion, 58, 82, 10.1016/j.inffus.2019.12.012 Miller, 2019, Explanation in artificial intelligence: Insights from the social sciences, Artificial Intelligence, 267, 1, 10.1016/j.artint.2018.07.007 Hendricks, 2018, Women also snowboard: Overcoming bias in captioning models, 793 Doran, 2017 Ribeiro, 2016 Ribeiro, 2016, Why should i trust you?: Explaining the predictions of any classifier, 1135 Lundberg, 2017, A unified approach to interpreting model predictions, 4765 Alvarez-Melis, 2018 Slack, 2019 Ras, 2021 R.R. Selvaraju, M. Cogswell, A. Das, R. Vedantam, D. Parikh, D. Batra, Grad-CAM: Visual explanations from deep networks via gradient-based localization, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 618–626. J. Adebayo, J. Gilmer, M. Muelly, I. Goodfellow, M. Hardt, B. Kim, Sanity checks for saliency maps, in: Proceedings of the International Conference on Neural Information Processing Systems, 2018, pp. 9505–9515. A. Bennetot, J.-L. Laurent, R. Chatila, N. Díaz-Rodríguez, Towards Explainable Neural-Symbolic Visual Reasoning, in: Proceedings of the Neural-Symbolic Learning and Reasoning Workshop, NeSy-2019 At International Joint Conference on Artificial Intelligence (IJCAI), Macau, China, 2019. Guidotti, 2018, A survey of methods for explaining black box models, ACM Comput. Surv., 51, 93:1 F.K. Dos̃ilović, M. Brc̃ić, N. Hlupić, Explainable artificial intelligence: A survey, in: 41st International Convention on Information and Communication Technology, Electronics and Microelectronics, MIPRO, 2018, pp. 210–215. I. Donadello, L. Serafini, A.D. Garcez, Logic tensor networks for semantic image interpretation, in: Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence, IJCAI, 2017, pp. 1596–1602. Donadello, 2018 d’Avila Garcez, 2019, Neural-symbolic computing: An effective methodology for principled integration of machine learning and reasoning, J. Appl. Log. IfCoLog J. Log. Appl. (FLAP), 6, 611 I. Donadello, M. Dragoni, C. Eccher, Persuasive Explanation of Reasoning Inferences on Dietary Data, in: First Workshop on Semantic Explainability @ ISWC 2019, 2019. Guidotti, 2018, A survey of methods for explaining black box models, ACM Comput. Surv. (CSUR), 51, 1, 10.1145/3236009 Buhrmester, 2019 Andreas, 2019 Fodor, 2002 Stone, 2017, Teaching compositionality to CNNs, 5058 Lake, 2015, Human-level concept learning through probabilistic program induction, Science, 350, 1332, 10.1126/science.aab3050 Hupkes, 2019 Mao, 2019 De Kok, 1999, Object-based classification and applications in the alpine forest environment, Int. Arch. Photogramm. Remote Sens., 32, 3 Huber, 2004, Parts-based 3d object classification, II Bernstein, 2005, Part-based statistical models for object classification and detection, 734 Felzenszwalb, 2009, Object detection with discriminatively trained part-based models, IEEE Trans. Pattern Anal. Mach. Intell., 32, 1627, 10.1109/TPAMI.2009.167 Everingham, 2012 W. Ge, X. Lin, Y. Yu, Weakly supervised complementary parts models for fine-grained image classification from the bottom up, in: Proceedings of the IEEE Conference on Computer Vision and Rattern Recognition, 2019, pp. 3034–3043. Holzinger, 2019, Causability and explainability of artificial intelligence in medicine, Wiley Interdiscip. Rev. Data Min. Knowl. Discov., 9, 10.1002/widm.1312 Holzinger, 2021, Towards multi-modal causability with graph neural networks enabling information fusion for explainable AI, Inf. Fusion, 71, 28, 10.1016/j.inffus.2021.01.008 Pearl, 2009 Holzinger, 2020, Measuring the quality of explanations: The system causability scale (SCS), KI - Künstliche Intelligenz, 34, 193, 10.1007/s13218-020-00636-z Hu, 2018, Squeeze-and-excitation networks, 7132 Steiner, 2021 Tolstikhin, 2021 J. Zhuang, B. Gong, L. Yuan, Y. Cui, H. Adam, N. Dvornek, S. Tatikonda, J. Duncan, T. Liu, Surrogate Gap Minimization Improves Sharpness-Aware Training, in: ICLR, 2022. A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, J. Uszkoreit, N. Houlsby, An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale, in: ICLR, 2021. Chen, 2021 X. Zhai, A. Kolesnikov, N. Houlsby, L. Beyer, Scaling Vision Transformers, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 12104–12113. A. Chavan, Z. Shen, Z. Liu, Z. Liu, K.-T. Cheng, E.P. Xing, Vision Transformer Slimming: Multi-Dimension Searching in Continuous Optimization Space, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 4931–4941. C. Zhang, M. Zhang, S. Zhang, D. Jin, Q. Zhou, Z. Cai, H. Zhao, X. Liu, Z. Liu, Delving Deep Into the Generalization of Vision Transformers Under Distribution Shifts, in: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR, 2022, pp. 7277–7286. Obeso, 2022, Visual vs internal attention mechanisms in deep neural networks for image classification and object detection, Pattern Recognit., 123, 10.1016/j.patcog.2021.108411 Díaz-Rodríguez, 2022, EXplainable Neural-Symbolic Learning (X-NeSyL) methodology to fuse deep learning representations with expert knowledge graphs: The MonuMAI cultural heritage use case, Information Fusion, 79, 58, 10.1016/j.inffus.2021.09.022 Garnelo, 2019, Reconciling deep learning with symbolic artificial intelligence: representing objects and relations, Curr. Opin. Behav. Sci., 29, 17, 10.1016/j.cobeha.2018.12.010 Manhaeve, 2018, DeepProbLog: Neural probabilistic logic programming, 3749 Petroni, 2019 Bollacker, 2019, Extending knowledge graphs with subjective influence networks for personalized fashion, 203 Shang, 2019 Aamodt, 1994, Case-based reasoning: Foundational issues, Methodol. Var. Syst. Approaches, 7, 39 R. Caruana, Case-Based Explanation for Artificial Neural Nets, in: Artificial Neural Networks in Medicine and Biology, Proceedings of the ANNIMAB-1 Conference, 2000, pp. 303–308. Keane, 2019 2007 Donadello, 2016, Integration of numeric and symbolic information for semantic image interpretation, Intelligenza Artificiale, 10, 33, 10.3233/IA-160093 Lamy, 2017, Formalization of the semantics of iconic languages: An ontology-based method and four semantic-powered applications, Knowl.-Based Syst., 135, 159, 10.1016/j.knosys.2017.08.011 Marra, 2019 Marra, 2019 Lipton, 2018, The mythos of model interpretability, Queue, 16, 30:31, 10.1145/3236386.3241340 Montavon, 2018, Methods for interpreting and understanding deep neural networks, Digit. Signal Process., 73, 1, 10.1016/j.dsp.2017.10.011 Bursac, 2008, Purposeful selection of variables in logistic regression, Source Code Biol. Med., 3, 17, 10.1186/1751-0473-3-17 Rokach, 2014 Imandoust, 2013, Application of k-nearest neighbor (knn) approach for predicting economic events: Theoretical background, Int. J. Eng. Res. Appl., 3, 605 Quinlan, 1987, Generating production rules from decision trees., 304 Berg, 2007, Bankruptcy prediction by generalized additive models, Appl. Stoch. Models Bus. Ind., 23, 129, 10.1002/asmb.658 Griffiths, 2008 Alvarez-Melis, 2018, Towards robust interpretability with self-explaining neural networks, 7786 Baum, 2004 Blundell, 2015 Kremen, 2009, Semantic annotation of objects, 223 Baader, 2003, 43 Auer, 2007, Dbpedia: A nucleus for a web of open data, 722 Miller, 1990, Introduction to WordNet: An on-line lexical database, Int. J. Lexicogr., 3, 235, 10.1093/ijl/3.4.235 Kiddon, 2012, Knowledge extraction and joint inference using tractable Markov logic, 79 Balasubramanian, 2012, Rel-grams: a probabilistic model of relations in text, 101 Hitzler, 2009 Antoniou, 2004, Web ontology language: Owl, 67 Norton, 2018, Log odds and the interpretation of logit models, Health Serv. Res., 53, 859, 10.1111/1475-6773.12712 Chen, 2018 Kervadec, 2020, Bounding boxes for weakly supervised segmentation: Global constraints get close to full supervision Lamas, 2020, MonuMAI: Dataset, deep learning pipeline and citizen science based app for monumental heritage taxonomy and classification, Neurocomputing, 420, 266, 10.1016/j.neucom.2020.09.041 Touvron, 2020 Sanfeliu, 1983, A distance measure between attributed relational graphs for pattern recognition, IEEE Trans. Syst. Man Cybern., 353, 10.1109/TSMC.1983.6313167 Jiang, 2021, Optimized loss functions for object detection and application on nighttime vehicle detection, Proc. Inst. Mech. Eng. D, 236, 1568, 10.1177/09544070211036366 Qin, 2018, Weighted focal loss: An effective loss function to overcome unbalance problem of chest X-ray14, IOP Conf. Ser. Mater. Sci. Eng., 428, 10.1088/1757-899X/428/1/012022 Wachter, 2017 R.K. Mothilal, A. Sharma, C. Tan, Explaining machine learning classifiers through diverse counterfactual explanations, in: Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, 2020, pp. 607–617. Del Ser, 2022 Verma, 2020 Dandl, 2020, Multi-objective counterfactual explanations, 448 Van Looveren, 2019 Karimi, 2019 Laugel, 2017 Ribeiro, 2018, Anchors: High-precision model-agnostic explanations Müller, 2021, Kandinsky patterns, Artificial Intelligence, 300, 10.1016/j.artint.2021.103546 Holzinger, 2019, KANDINSKY patterns as IQ-test for machine learning, 1