{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T08:32:17Z","timestamp":1768293137443,"version":"3.49.0"},"reference-count":22,"publisher":"Association for Computing Machinery (ACM)","issue":"2","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["SIGKDD Explor. Newsl."],"published-print":{"date-parts":[[2025,12,30]]},"abstract":"<jats:p>In the field of explainable AI (XAI), a significant challenge lies in the evaluation of explanation methods. State-ofthe- art techniques identify the importance of input features (e.g., pixels) for the classification, based on untestable assumptions about the model. Lowering the intensity of pixels, identified as irrelevant, typically leads to a change in the predicted class. To address this, we propose SpaCEVAE, a Variational Autoencoder (VAE) designed to generate sparse, confident explanations that are inherently evaluable. SpaCE-VAE produces a sparse representation of an image, putting as many pixels as possible to black, such that the resulting image is still assigned to the same class as the original image (with high confidence).<\/jats:p>","DOI":"10.1145\/3787470.3787485","type":"journal-article","created":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:46:21Z","timestamp":1767228381000},"page":"142-148","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["SpaCE-VAE: Sparse and Confident Explanations usingVariational Autoencoders"],"prefix":"10.1145","volume":"27","author":[{"given":"Alexander","family":"Liu","sequence":"first","affiliation":[{"name":"Eindhoven University of Technology Groene Loper 5, Eindhoven, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sibylle","family":"Hess","sequence":"additional","affiliation":[{"name":"Eindhoven University of Technology Groene Loper 5, Eindhoven, Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,31]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"e_1_2_1_2_1","volume-title":"Deep convolutional networks do not classify based on global object shape. PLoS computational biology","author":"Baker N.","year":"2018","unstructured":"N. Baker, H. Lu, G. Erlikhman, and P. J. Kellman. Deep convolutional networks do not classify based on global object shape. PLoS computational biology, 2018."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-30047-9_8"},{"key":"e_1_2_1_4_1","volume-title":"VISIGRAPP : VISAPP","author":"da Costa Feitosa J.","year":"2024","unstructured":"J. da Costa Feitosa, M. Roder, J. P. Papa, and J. R. F. Brega. Influence of pixel perturbation on explainable artificial intelligence methods. In VISIGRAPP : VISAPP, 2024."},{"key":"e_1_2_1_5_1","volume-title":"Neural Information Processing Systems","author":"Dabkowski P.","year":"2017","unstructured":"P. Dabkowski and Y. Gal. Real time image saliency for black box classifiers. In Neural Information Processing Systems, 2017."},{"key":"e_1_2_1_6_1","volume-title":"ACM Computing Surveys","author":"Dwivedi R.","year":"2023","unstructured":"R. Dwivedi, D. Dave, H. Naik, S. Singhal, R. Omer, P. Patel, B. Qian, Z. Wen, T. Shah, G. Morgan, et al. Explainable ai (xai): Core ideas, techniques, and solutions. ACM Computing Surveys, 2023."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.371"},{"key":"e_1_2_1_8_1","volume-title":"7th International Conference on Learning Representations (ICLR)","author":"Geirhos R.","year":"2019","unstructured":"R. Geirhos, P. Rubisch, C. Michaelis, M. Bethge, F. A. Wichmann, and W. Brendel. Imagenet-trained cnns are biased towards texture; increasing shape bias improves accuracy and robustness. In 7th International Conference on Learning Representations (ICLR), 2019."},{"key":"e_1_2_1_9_1","volume-title":"et al. Captum: A unified and generic model interpretability library for pytorch. arXiv preprint arXiv:2009.07896","author":"Kokhlikyan N.","year":"2020","unstructured":"N. Kokhlikyan, V. Miglani, M. Martin, E. Wang, B. Alsallakh, J. Reynolds, A. Melnikov, N. Kliushkina, C. Araya, S. Yan, et al. Captum: A unified and generic model interpretability library for pytorch. arXiv preprint arXiv:2009.07896, 2020."},{"key":"e_1_2_1_10_1","volume-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky A.","year":"2009","unstructured":"A. Krizhevsky, G. Hinton, et al. Learning multiple layers of features from tiny images. 2009."},{"key":"e_1_2_1_11_1","volume-title":"Proceedings of the fifth Berkeley symposium on mathematical statistics and probability","author":"MacQueen J.","year":"1967","unstructured":"J. MacQueen et al. Some methods for classification and analysis of multivariate observations. In Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, 1967."},{"key":"e_1_2_1_12_1","volume-title":"Interpretable Machine Learning. 3 edition","author":"Molnar C.","year":"2025","unstructured":"C. Molnar. Interpretable Machine Learning. 3 edition, 2025."},{"key":"e_1_2_1_13_1","volume-title":"Advances in Neural Information Processing Systems","author":"Nguyen G.","year":"2021","unstructured":"G. Nguyen, D. Kim, and A. Nguyen. The effectiveness of feature attribution methods and its correlation with automatic evaluation scores. Advances in Neural Information Processing Systems, 2021."},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00998"},{"key":"e_1_2_1_15_1","volume-title":"Generating diverse high-fidelity images with vq-vae-2. Advances in neural information processing systems","author":"Razavi A.","year":"2019","unstructured":"A. Razavi, A. Van den Oord, and O. Vinyals. Generating diverse high-fidelity images with vq-vae-2. Advances in neural information processing systems, 2019."},{"key":"e_1_2_1_16_1","volume-title":"International Conference on Machine Learning","author":"Rong Y.","year":"2022","unstructured":"Y. Rong, T. Leemann, V. Borisov, G. Kasneci, and E. Kasneci. A consistent and efficient evaluation strategy for attribution methods. In International Conference on Machine Learning, 2022."},{"key":"e_1_2_1_17_1","volume-title":"International conference on machine learning","author":"Shrikumar A.","year":"2017","unstructured":"A. Shrikumar, P. Greenside, and A. Kundaje. Learning important features through propagating activation differences. In International conference on machine learning, 2017."},{"key":"e_1_2_1_18_1","volume-title":"Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034","author":"Simonyan K.","year":"2013","unstructured":"K. Simonyan, A. Vedaldi, and A. Zisserman. Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint arXiv:1312.6034, 2013."},{"key":"e_1_2_1_19_1","volume-title":"International conference on machine learning","author":"Sundararajan M.","year":"2017","unstructured":"M. Sundararajan, A. Taly, and Q. Yan. Axiomatic attribution for deep networks. In International conference on machine learning, 2017."},{"key":"e_1_2_1_20_1","volume-title":"2nd International Conference on Learning Representations (ICLR)","author":"Szegedy C.","year":"2014","unstructured":"C. Szegedy, W. Zaremba, I. Sutskever, J. Bruna, D. Erhan, I. J. Goodfellow, and R. Fergus. Intriguing properties of neural networks. In 2nd International Conference on Learning Representations (ICLR), 2014."},{"key":"e_1_2_1_21_1","volume-title":"Neural discrete representation learning. Advances in neural information processing systems","author":"Van Den Oord A.","year":"2017","unstructured":"A. Van Den Oord, O. Vinyals, et al. Neural discrete representation learning. Advances in neural information processing systems, 2017."},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"}],"container-title":["ACM SIGKDD Explorations Newsletter"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3787470.3787485","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T00:43:47Z","timestamp":1768265027000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3787470.3787485"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,30]]},"references-count":22,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,12,30]]}},"alternative-id":["10.1145\/3787470.3787485"],"URL":"https:\/\/doi.org\/10.1145\/3787470.3787485","relation":{},"ISSN":["1931-0145","1931-0153"],"issn-type":[{"value":"1931-0145","type":"print"},{"value":"1931-0153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,30]]},"assertion":[{"value":"2025-12-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}