{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/robust-multimodal-survival-prediction-with","title":"Robust Multimodal Survival Prediction with the Latent Differentiation Conditional Variational AutoEncoder","arxiv_id":"2503.09496","date":"2025-03-12","proceeding":null,"authors":["Junjie Zhou","Jiao Tang","Yingli Zuo","Peng Wan","Daoqiang Zhang","Wei Shao"],"abstract":"The integrative analysis of histopathological images and genomic data has received increasing attention for survival prediction of human cancers. However, the existing studies always hold the assumption that full modalities are available. As a matter of fact, the cost for collecting genomic data is high, which sometimes makes genomic data unavailable in testing samples. A common way of tackling such incompleteness is to generate the genomic representations from the pathology images. Nevertheless, such strategy still faces the following two challenges: (1) The gigapixel whole slide images (WSIs) are huge and thus hard for representation. (2) It is difficult to generate the genomic embeddings with diverse function categories in a unified generative framework. To address the above challenges, we propose a Conditional Latent Differentiation Variational AutoEncoder (LD-CVAE) for robust multimodal survival prediction, even with missing genomic data. Specifically, a Variational Information Bottleneck Transformer (VIB-Trans) module is proposed to learn compressed pathological representations from the gigapixel WSIs. To generate different functional genomic features, we develop a novel Latent Differentiation Variational AutoEncoder (LD-VAE) to learn the common and specific posteriors for the genomic embeddings with diverse functions. Finally, we use the product-of-experts technique to integrate the genomic common posterior and image posterior for the joint latent distribution estimation in LD-CVAE. We test the effectiveness of our method on five different cancer datasets, and the experimental results demonstrate its superiority in both complete and missing modality scenarios.","url_abs":"https://arxiv.org/abs/2503.09496v1","url_pdf":"https://arxiv.org/pdf/2503.09496v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"robust-multimodal-survival-prediction-with","repo_url":"https://github.com/JJ-ZHOU-Code/RobustMultiModel","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"survival-prediction","task_name":"Survival Prediction"},{"task_slug":"whole-slide-images","task_name":"whole slide images"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"bottleneck-transformer","method_name":"Bottleneck Transformer"},{"method_slug":"bottleneck-transformer-block","method_name":"Bottleneck Transformer Block"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"pointwise-convolution","method_name":"Pointwise Convolution"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2503.09496","atlas_url":"https://app.syntology.ai/?focus=2503.09496","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.09496"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/JJ-ZHOU-Code/RobustMultiModel","reach":null}],"summary":{"ran":4,"ran_draft_wrong":2},"by_repo_kind":{"official":{"samples":5,"ran":5,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":6,"samples":[{"code_sha256_prefix":"44e3a3d761a3d791","entry":"Decoder_Share","repo":"JJ-ZHOU-Code/RobustMultiModel","repo_kind":"official","path":"models/model_ldvae.py","file_url":"https://github.com/JJ-ZHOU-Code/RobustMultiModel/blob/HEAD/models/model_ldvae.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"44e3a3d761a3d791"}},{"code_sha256_prefix":"796cffef10d94448","entry":"Decoder_Specific","repo":"JJ-ZHOU-Code/RobustMultiModel","repo_kind":"official","path":"models/model_ldvae.py","file_url":"https://github.com/JJ-ZHOU-Code/RobustMultiModel/blob/HEAD/models/model_ldvae.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"796cffef10d94448"}},{"code_sha256_prefix":"5cf9ee8e784759c2","entry":"Encoder_TRANSFORMER","repo":"JJ-ZHOU-Code/RobustMultiModel","repo_kind":"official","path":"models/model_ldvae.py","file_url":"https://github.com/JJ-ZHOU-Code/RobustMultiModel/blob/HEAD/models/model_ldvae.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5cf9ee8e784759c2"}},{"code_sha256_prefix":"933b8e67ac23c0ad","entry":"LDVAE","repo":"JJ-ZHOU-Code/RobustMultiModel","repo_kind":"official","path":"models/model_ldvae.py","file_url":"https://github.com/JJ-ZHOU-Code/RobustMultiModel/blob/HEAD/models/model_ldvae.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"933b8e67ac23c0ad"}},{"code_sha256_prefix":"28023ddd28326523","entry":"prior_expert","repo":"JJ-ZHOU-Code/RobustMultiModel","repo_kind":"official","path":"models/model_ldvae.py","file_url":"https://github.com/JJ-ZHOU-Code/RobustMultiModel/blob/HEAD/models/model_ldvae.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"28023ddd28326523"}},{"code_sha256_prefix":"3cd91116c815d020","entry":"reparameterize","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"3cd91116c815d020"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}