{"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/understanding-multimodal-contrastive-learning-1","title":"Weighted Point Cloud Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metric","arxiv_id":"2404.19228","date":"2024-04-30","proceeding":null,"authors":["Toshimitsu Uesaka","Taiji Suzuki","Yuhta Takida","Chieh-Hsin Lai","Naoki Murata","Yuki Mitsufuji"],"abstract":"In typical multimodal contrastive learning, such as CLIP, encoders produce one point in the latent representation space for each input. However, one-point representation has difficulty in capturing the relationship and the similarity structure of a huge amount of instances in the real world. For richer classes of the similarity, we propose the use of weighted point clouds, namely, sets of pairs of weight and vector, as representations of instances. In this work, we theoretically show the benefit of our proposed method through a new understanding of the contrastive loss of CLIP, which we call symmetric InfoNCE. We clarify that the optimal similarity that minimizes symmetric InfoNCE is the pointwise mutual information, and show an upper bound of excess risk on downstream classification tasks of representations that achieve the optimal similarity. In addition, we show that our proposed similarity based on weighted point clouds consistently achieves the optimal similarity. To verify the effectiveness of our proposed method, we demonstrate pretraining of text-image representation models and classification tasks on common benchmarks.","url_abs":"https://arxiv.org/abs/2404.19228v2","url_pdf":"https://arxiv.org/pdf/2404.19228v2.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":[],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"zero-shot-learning","task_name":"Zero-Shot Learning"}],"methods":[{"method_slug":"clip","method_name":"CLIP"},{"method_slug":"contrastive-learning","method_name":"Contrastive Learning"},{"method_slug":"infonce","method_name":"InfoNCE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2404.19228","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2404.19228"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/sony/wpse","reach":null}],"summary":{"ran":5,"unverified":2},"by_repo_kind":{"found_in_text":{"samples":7,"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":0,"samples":[{"code_sha256_prefix":"d9cfd173bee635fd","entry":"LayerNorm","repo":"sony/wpse","repo_kind":"found_in_text","path":"models.py","file_url":"https://github.com/sony/wpse/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d9cfd173bee635fd"}},{"code_sha256_prefix":"04768da6a78b1f32","entry":"LogitScaleExp","repo":"sony/wpse","repo_kind":"found_in_text","path":"models.py","file_url":"https://github.com/sony/wpse/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"04768da6a78b1f32"}},{"code_sha256_prefix":"f2503a5f57b01bae","entry":"QuickGELU","repo":"sony/wpse","repo_kind":"found_in_text","path":"models.py","file_url":"https://github.com/sony/wpse/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f2503a5f57b01bae"}},{"code_sha256_prefix":"7f9563e94f649f1c","entry":"ResidualAttentionBlock","repo":"sony/wpse","repo_kind":"found_in_text","path":"models.py","file_url":"https://github.com/sony/wpse/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7f9563e94f649f1c"}},{"code_sha256_prefix":"943944a356054cb5","entry":"Transformer","repo":"sony/wpse","repo_kind":"found_in_text","path":"models.py","file_url":"https://github.com/sony/wpse/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"943944a356054cb5"}},{"code_sha256_prefix":"07ea912271e29c92","entry":"CLIP","repo":"sony/wpse","repo_kind":"found_in_text","path":"models.py","file_url":"https://github.com/sony/wpse/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"07ea912271e29c92"}},{"code_sha256_prefix":"c12d9ae49d78a6f6","entry":"CLIP_WPSE_two_proj","repo":"sony/wpse","repo_kind":"found_in_text","path":"models.py","file_url":"https://github.com/sony/wpse/blob/HEAD/models.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c12d9ae49d78a6f6"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}