{"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/kernel-ssl-kernel-kl-divergence-for-self","title":"Matrix Information Theory for Self-Supervised Learning","arxiv_id":"2305.17326","date":"2023-05-27","proceeding":null,"authors":["Yifan Zhang","Zhiquan Tan","Jingqin Yang","Weiran Huang","Yang Yuan"],"abstract":"The maximum entropy encoding framework provides a unified perspective for many non-contrastive learning methods like SimSiam, Barlow Twins, and MEC. Inspired by this framework, we introduce Matrix-SSL, a novel approach that leverages matrix information theory to interpret the maximum entropy encoding loss as matrix uniformity loss. Furthermore, Matrix-SSL enhances the maximum entropy encoding method by seamlessly incorporating matrix alignment loss, directly aligning covariance matrices in different branches. Experimental results reveal that Matrix-SSL outperforms state-of-the-art methods on the ImageNet dataset under linear evaluation settings and on MS-COCO for transfer learning tasks. Specifically, when performing transfer learning tasks on MS-COCO, our method outperforms previous SOTA methods such as MoCo v2 and BYOL up to 3.3% with only 400 epochs compared to 800 epochs pre-training. We also try to introduce representation learning into the language modeling regime by fine-tuning a 7B model using matrix cross-entropy loss, with a margin of 3.1% on the GSM8K dataset over the standard cross-entropy loss. Code available at https://github.com/yifanzhang-pro/Matrix-SSL.","url_abs":"https://arxiv.org/abs/2305.17326v7","url_pdf":"https://arxiv.org/pdf/2305.17326v7.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":"kernel-ssl-kernel-kl-divergence-for-self","repo_url":"https://github.com/yifanzhang-pro/matrix-llm","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"kernel-ssl-kernel-kl-divergence-for-self","repo_url":"https://github.com/yifanzhang-pro/matrix-ssl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"kernel-ssl-kernel-kl-divergence-for-self","repo_url":"https://github.com/huang-research-group/Matrix-SSL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"contrastive-learning","task_name":"Contrastive Learning"},{"task_slug":"gsm8k","task_name":"GSM8K"},{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"linear-evaluation","task_name":"Linear evaluation"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"1x1-convolution","method_name":"1x1 Convolution"},{"method_slug":"average-pooling","method_name":"Average Pooling"},{"method_slug":"byol","method_name":"BYOL"},{"method_slug":"barlow-twins","method_name":"Barlow Twins"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"bottleneck-residual-block","method_name":"Bottleneck Residual Block"},{"method_slug":"colorjitter","method_name":"ColorJitter"},{"method_slug":"convolution","method_name":"Convolution"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"feedforward-network","method_name":"Feedforward Network"},{"method_slug":"global-average-pooling","method_name":"Global Average Pooling"},{"method_slug":"infonce","method_name":"InfoNCE"},{"method_slug":"kaiming-initialization","method_name":"Kaiming Initialization"},{"method_slug":"max-pooling","method_name":"Max Pooling"},{"method_slug":"moco","method_name":"MoCo"},{"method_slug":"moco-v2","method_name":"MoCo v2"},{"method_slug":"nt-xent","method_name":"NT-Xent"},{"method_slug":"random-gaussian-blur","method_name":"Random Gaussian Blur"},{"method_slug":"random-resized-crop","method_name":"Random Resized Crop"},{"method_slug":"relu","method_name":"ReLU"},{"method_slug":"residual-block","method_name":"Residual Block"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"simclr","method_name":"SimCLR"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/contrastive-learning-on-imagenet-1k","task":"Contrastive Learning","dataset":"imagenet-1k","model":"ResNet50","rank_in_archive_order":1,"of":14,"metrics":{"ImageNet Top-1 Accuracy":"73.6"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2305.17326","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.17326"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yifanzhang-pro/matrix-ssl","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huang-research-group/Matrix-SSL","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yifanzhang-pro/matrix-llm","reach":{"status":"ok"}}],"summary":{"ran_fixture":3,"ran_honours":1,"ran_draft_wrong":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":5,"samples":[{"code_sha256_prefix":"131a82fd65128218","entry":"accuracy","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"131a82fd65128218"}},{"code_sha256_prefix":"6f50e99cc54dcded","entry":"centering_matrix","repo":"yifanzhang-pro/matrix-ssl","repo_kind":"official","path":"main_pretrain.py","file_url":"https://github.com/yifanzhang-pro/matrix-ssl/blob/HEAD/main_pretrain.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"6f50e99cc54dcded"}},{"code_sha256_prefix":"1d1166c3c8576e62","entry":"matrix_log","repo":"yifanzhang-pro/matrix-ssl","repo_kind":"official","path":"main_pretrain.py","file_url":"https://github.com/yifanzhang-pro/matrix-ssl/blob/HEAD/main_pretrain.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"1d1166c3c8576e62"}},{"code_sha256_prefix":"987edac09a4b3811","entry":"mce_loss_func","repo":"yifanzhang-pro/matrix-ssl","repo_kind":"official","path":"main_pretrain.py","file_url":"https://github.com/yifanzhang-pro/matrix-ssl/blob/HEAD/main_pretrain.py","link_basis":"first_harvest_node","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"987edac09a4b3811"}},{"code_sha256_prefix":"63ce1d5edf8fb0a0","entry":"validate","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"63ce1d5edf8fb0a0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}