{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T23:34:47Z","timestamp":1762040087791,"version":"build-2065373602"},"publisher-location":"California","reference-count":0,"publisher":"International Joint Conferences on Artificial Intelligence Organization","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,8]]},"abstract":"<jats:p>Several methods have recently been developed for computing attributions of a neural network's prediction over the input features. However, these existing approaches for computing attributions are noisy and not robust to small perturbations of the input. This paper uses the recently identified connection between dynamical systems and residual neural networks to show that the attributions computed over neural stochastic differential equations (SDEs) are less noisy, visually sharper, and quantitatively more robust. Using dynamical systems theory, we theoretically analyze the robustness of these attributions. We also experimentally demonstrate the efficacy of our approach in providing smoother, visually sharper and quantitatively robust attributions by computing attributions for ImageNet images using ResNet-50, WideResNet-101 models and ResNeXt-101 models.<\/jats:p>","DOI":"10.24963\/ijcai.2021\/73","type":"proceedings-article","created":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T11:00:49Z","timestamp":1628679649000},"page":"522-528","source":"Crossref","is-referenced-by-count":6,"title":["On Smoother Attributions using Neural Stochastic Differential Equations"],"prefix":"10.24963","author":[{"given":"Sumit","family":"Jha","sequence":"first","affiliation":[{"name":"University of Texas at San Antonio, San Antonio, TX"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rickard","family":"Ewetz","sequence":"additional","affiliation":[{"name":"University of Central Florida, Orlando, FL"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alvaro","family":"Velasquez","sequence":"additional","affiliation":[{"name":"Air Force Research Laboratory, Rome, NY"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Susmit","family":"Jha","sequence":"additional","affiliation":[{"name":"SRI International, Menlo Park, CA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"10584","event":{"number":"30","sponsor":["International Joint Conferences on Artificial Intelligence Organization (IJCAI)"],"acronym":"IJCAI-2021","name":"Thirtieth International Joint Conference on Artificial Intelligence {IJCAI-21}","start":{"date-parts":[[2021,8,19]]},"theme":"Artificial Intelligence","location":"Montreal, Canada","end":{"date-parts":[[2021,8,27]]}},"container-title":["Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence"],"original-title":[],"deposited":{"date-parts":[[2021,8,11]],"date-time":"2021-08-11T11:01:13Z","timestamp":1628679673000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ijcai.org\/proceedings\/2021\/73"}},"subtitle":[],"proceedings-subject":"Artificial Intelligence Research Articles","short-title":[],"issued":{"date-parts":[[2021,8]]},"references-count":0,"URL":"https:\/\/doi.org\/10.24963\/ijcai.2021\/73","relation":{},"subject":[],"published":{"date-parts":[[2021,8]]}}}