{"id":7208,"date":"2025-09-29T07:02:31","date_gmt":"2025-09-29T07:02:31","guid":{"rendered":"https:\/\/mailitics.com\/index.php\/2025\/09\/29\/2509-21584\/"},"modified":"2025-09-29T07:02:31","modified_gmt":"2025-09-29T07:02:31","slug":"2509-21584","status":"publish","type":"post","link":"https:\/\/mailitics.com\/index.php\/2025\/09\/29\/2509-21584\/","title":{"rendered":"IndiSeek learns information-guided disentangled representations"},"content":{"rendered":"

IndiSeek learns information-guided disentangled representations
\n \t

\n
<\/BR>
\n
\n \t

\n
<\/BR><\/p>\n

arXiv:2509.21584v1 Announce Type: new
\nAbstract: Learning disentangled representations is a fundamental task in multi-modal learning. In modern applications such as single-cell multi-omics, both shared and modality-specific features are critical for characterizing cell states and supporting downstream analyses. Ideally, modality-specific features should be independent of shared ones while also capturing all complementary information within each modality. This tradeoff is naturally expressed through information-theoretic criteria, but mutual-information-based objectives are difficult to estimate reliably, and their variational surrogates often underperform in practice. In this paper, we introduce IndiSeek, a novel disentangled representation learning approach that addresses this challenge by combining an independence-enforcing objective with a computationally efficient reconstruction loss that bounds conditional mutual information. This formulation explicitly balances independence and completeness, enabling principled extraction of modality-specific features. We demonstrate the effectiveness of IndiSeek on synthetic simulations, a CITE-seq dataset and multiple real-world multi-modal benchmarks.<\/div>\n

\t

\n
<\/BR>
\n Yu Gui, Cong Ma, Zongming Ma
\n \t

\n
<\/BR>
\nGo to original source<\/a>
\n \t

\n
<\/BR><\/p>\n","protected":false},"excerpt":{"rendered":"

IndiSeek learns information-guided disentangled representations arXiv:2509.21584v1 Announce Type: new Abstract: Learning disentangled representations is a fundamental task in multi-modal learning. In modern applications such as single-cell multi-omics, both shared and modality-specific features are critical for characterizing cell states and supporting downstream analyses. Ideally, modality-specific features should be independent of shared ones while also capturing all […]<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[62,113,112],"tags":[3916,3915,458],"class_list":["post-7208","post","type-post","status-publish","format-standard","hentry","category-aimldsaimlds","category-cs-lg","category-stat-ml","tag-disentangled","tag-indiseek","tag-information"],"_links":{"self":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/7208"}],"collection":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/comments?post=7208"}],"version-history":[{"count":0,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/posts\/7208\/revisions"}],"wp:attachment":[{"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/media?parent=7208"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/categories?post=7208"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/mailitics.com\/index.php\/wp-json\/wp\/v2\/tags?post=7208"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}