{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:20:00Z","timestamp":1750220400123,"version":"3.41.0"},"reference-count":55,"publisher":"Association for Computing Machinery (ACM)","issue":"3s","license":[{"start":{"date-parts":[[2021,10,31]],"date-time":"2021-10-31T00:00:00Z","timestamp":1635638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"JSPS","award":["JP18H03339 and JP19K20289"],"award-info":[{"award-number":["JP18H03339 and JP19K20289"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Multimedia Comput. Commun. Appl."],"published-print":{"date-parts":[[2021,10,31]]},"abstract":"<jats:p>Given the promising results obtained by deep-learning techniques in multimedia analysis, the explainability of predictions made by networks has become important in practical applications. We present a method to generate semantic and quantitative explanations that are easily interpretable by humans. The previous work to obtain such explanations has focused on the contributions of each feature, taking their sum to be the prediction result for a target variable; the lack of discriminative power due to this simple additive formulation led to low explanatory performance. Our method considers not only individual features but also their interactions, for a more detailed interpretation of the decisions made by networks. The algorithm is based on the factorization machine, a prediction method that calculates factor vectors for each feature. We conducted experiments on multiple datasets with different models to validate our method, achieving higher performance than the previous work. We show that including interactions not only generates explanations but also makes them richer and is able to convey more information. We show examples of produced explanations in a simple visual format and verify that they are easily interpretable and plausible.<\/jats:p>","DOI":"10.1145\/3474557","type":"journal-article","created":{"date-parts":[[2021,11,15]],"date-time":"2021-11-15T17:56:12Z","timestamp":1636998972000},"page":"1-19","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Semantic Explanation for Deep Neural Networks Using Feature Interactions"],"prefix":"10.1145","volume":"17","author":[{"given":"Bohui","family":"Xia","sequence":"first","affiliation":[{"name":"The University of Tokyo, Tokyo, Japan"}]},{"given":"Xueting","family":"Wang","sequence":"additional","affiliation":[{"name":"The University of Tokyo, Tokyo, Japan"}]},{"given":"Toshihiko","family":"Yamasaki","sequence":"additional","affiliation":[{"name":"The University of Tokyo, Tokyo, Japan"}]}],"member":"320","published-online":{"date-parts":[[2021,11,15]]},"reference":[{"issue":"210","key":"e_1_3_3_2_2","first-page":"1","article-title":"ProtoAttend: Attention-based prototypical learning","volume":"21","author":"Arik Sercan O.","year":"2020","unstructured":"Sercan O. Arik and Tomas Pfister. 2020. ProtoAttend: Attention-based prototypical learning. Journal of Machine Learning Research 21, 210 (2020), 1\u201335.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455088"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00928"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157340"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/2988450.2988454"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.5555\/3157382.3157490"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_3_9_2","article-title":"Visualizing higher-layer features of a deep network","author":"Erhan Dumitru","year":"2009","unstructured":"Dumitru Erhan, Yoshua Bengio, Aaron Courville, and Pascal Vincent. 2009. Visualizing higher-layer features of a deep network. Technical Report, Univerist\u00e9 de Montr\u00e9al.","journal-title":"Technical Report, Univerist\u00e9 de Montr\u00e9al"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1214\/07-AOAS148"},{"key":"e_1_3_3_11_2","unstructured":"Nicholas Frosst and Geoffrey E. Hinton. 2017. Distilling a Neural Network Into a Soft Decision Tree. arxiv:1711.09784."},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.5555\/3172077.3172127"},{"key":"e_1_3_3_13_2","unstructured":"Michael Harradon Jeff Druce and Brian Ruttenberg. 2018. Causal Learning and Explanation of Deep Neural Networks via Autoencoded Activations. arxiv:1802.00541."},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_17"},{"key":"e_1_3_3_16_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Higgins Irina","year":"2017","unstructured":"Irina Higgins, Lo\u00efc Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew Botvinick, Shakir Mohamed, and Alexander Lerchner. 2017. beta-VAE: Learning basic visual concepts with a constrained variational framework. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2939201"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00880"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00879"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_35"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1401944"},{"key":"e_1_3_3_22_2","unstructured":"Jiwei Li Will Monroe and Dan Jurafsky. 2017. Understanding Neural Networks through Representation Erasure. arxiv:1612.08220."},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.5555\/3504035.3504467"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220023"},{"key":"e_1_3_3_25_2","volume-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition","author":"Liu Ziwei","year":"2016","unstructured":"Ziwei Liu, Ping Luo, Shi Qiu, Xiaogang Wang, and Xiaoou Tang. 2016. DeepFashion: Powering robust clothes recognition and retrieval with rich annotations. In Proceedings of IEEE Conference on Computer Vision and Pattern Recognition."},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487579"},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299155"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330908"},{"key":"e_1_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2979670"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2905015"},{"key":"e_1_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00915"},{"key":"e_1_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3233770"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.5555\/3504035.3504222"},{"key":"e_1_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.5555\/3305890.3306006"},{"key":"e_1_3_3_39_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_3_40_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Singh Chandan","year":"2019","unstructured":"Chandan Singh, W. James Murdoch, and Bin Yu. 2019. Hierarchical interpretations for neural network predictions. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357925"},{"key":"e_1_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.5555\/2976040.2976207"},{"key":"e_1_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.85"},{"key":"e_1_3_3_44_2","first-page":"1H4OS12b01\u20131H4O","volume-title":"Proceedings of the Annual Conference of JSAI","author":"Tao Li","year":"2020","unstructured":"Li Tao, Xueting Wang, Tatsuya Kawahara, and Toshihiko Yamasaki. 2020. Television advertisement analysis using attention-based multimodal network. In Proceedings of the Annual Conference of JSAI. 1H4OS12b01\u20131H4OS12b01."},{"key":"e_1_3_3_45_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Tsang Michael","year":"2020","unstructured":"Michael Tsang, Dehua Cheng, Hanpeng Liu, Xue Feng, Eric Zhou, and Yan Liu. 2020. Feature interaction interpretability: A case for explaining ad-recommendation systems via neural interaction detection. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1145\/3124749.3124754"},{"key":"e_1_3_3_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2982166"},{"key":"e_1_3_3_48_2","unstructured":"Ning Xie Gabrielle Ras Marcel van Gerven and Derek Doran. 2020. Explainable Deep Learning: A Field Guide for the Uninitiated. arxiv:2004.14545."},{"key":"e_1_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539957"},{"key":"e_1_3_3_50_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"e_1_3_3_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"e_1_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.5555\/3504035.3504581"},{"key":"e_1_3_3_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00920"},{"key":"e_1_3_3_54_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-30671-1_4"},{"key":"e_1_3_3_55_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Zhou Bolei","year":"2015","unstructured":"Bolei Zhou, Aditya Khosla, \u00c0gata Lapedriza, Aude Oliva, and Antonio Torralba. 2015. Object detectors emerge in deep scene CNNs. In Proceedings of the International Conference on Learning Representations."},{"key":"e_1_3_3_56_2","volume-title":"Proceedings of the International Conference on Learning Representations","author":"Zintgraf Luisa M.","year":"2017","unstructured":"Luisa M. Zintgraf, Taco S. Cohen, Tameem Adel, and Max Welling. 2017. Visualizing deep neural network decisions: Prediction difference analysis. In Proceedings of the International Conference on Learning Representations."}],"container-title":["ACM Transactions on Multimedia Computing, Communications, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474557","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3474557","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:18:50Z","timestamp":1750191530000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3474557"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,31]]},"references-count":55,"journal-issue":{"issue":"3s","published-print":{"date-parts":[[2021,10,31]]}},"alternative-id":["10.1145\/3474557"],"URL":"https:\/\/doi.org\/10.1145\/3474557","relation":{},"ISSN":["1551-6857","1551-6865"],"issn-type":[{"type":"print","value":"1551-6857"},{"type":"electronic","value":"1551-6865"}],"subject":[],"published":{"date-parts":[[2021,10,31]]},"assertion":[{"value":"2020-12-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-07-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-11-15","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}