{"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/tod-tensor-based-outlier-detection","title":"TOD: GPU-accelerated Outlier Detection via Tensor Operations","arxiv_id":"2110.14007","date":"2021-10-26","proceeding":null,"authors":["Yue Zhao","George H. Chen","Zhihao Jia"],"abstract":"Outlier detection (OD) is a key learning task for finding rare and deviant data samples, with many time-critical applications such as fraud detection and intrusion detection. In this work, we propose TOD, the first tensor-based system for efficient and scalable outlier detection on distributed multi-GPU machines. A key idea behind TOD is decomposing complex OD applications into a small collection of basic tensor algebra operators. This decomposition enables TOD to accelerate OD computations by leveraging recent advances in deep learning infrastructure in both hardware and software. Moreover, to deploy memory-intensive OD applications on modern GPUs with limited on-device memory, we introduce two key techniques. First, provable quantization speeds up OD computations and reduces its memory footprint by automatically performing specific floating-point operations in lower precision while provably guaranteeing no accuracy loss. Second, to exploit the aggregated compute resources and memory capacity of multiple GPUs, we introduce automatic batching, which decomposes OD computations into small batches for both sequential execution on a single GPU and parallel execution on multiple GPUs. TOD supports a diverse set of OD algorithms. Extensive evaluation on 11 real and 3 synthetic OD datasets shows that TOD is on average 10.9x faster than the leading CPU-based OD system PyOD (with a maximum speedup of 38.9x), and can handle much larger datasets than existing GPU-based OD systems. In addition, TOD allows easy integration of new OD operators, enabling fast prototyping of emerging and yet-to-discovered OD algorithms.","url_abs":"https://arxiv.org/abs/2110.14007v3","url_pdf":"https://arxiv.org/pdf/2110.14007v3.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":"tod-tensor-based-outlier-detection","repo_url":"https://github.com/yzhao062/pytod","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-2-Clause"}},{"paper_slug":"tod-tensor-based-outlier-detection","repo_url":"https://github.com/yzhao062/yzhao062","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"CPU"},{"task_slug":"fraud-detection","task_name":"Fraud Detection"},{"task_slug":null,"task_name":"GPU"},{"task_slug":"intrusion-detection","task_name":"Intrusion Detection"},{"task_slug":"outlier-detection","task_name":"Outlier Detection"},{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"tensor-algebra","task_name":"tensor algebra"}],"methods":[{"method_slug":"pca","method_name":"PCA"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2110.14007","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.14007"}},"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/yzhao062/yzhao062","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yzhao062/pytod","reach":{"status":"ok","spdx":"BSD-2-Clause"}}],"summary":{"unverified":10},"by_repo_kind":{"official":{"samples":10,"ran":0,"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":"eed9bac1258c0a25","entry":"bottomk","repo":"yzhao062/pytod","repo_kind":"official","path":"pytod/models/basic_operators.py","file_url":"https://github.com/yzhao062/pytod/blob/HEAD/pytod/models/basic_operators.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"eed9bac1258c0a25"}},{"code_sha256_prefix":"1d682e1efc95584b","entry":"bottomk_batch","repo":"yzhao062/pytod","repo_kind":"official","path":"pytod/models/basic_operators_batch.py","file_url":"https://github.com/yzhao062/pytod/blob/HEAD/pytod/models/basic_operators_batch.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"1d682e1efc95584b"}},{"code_sha256_prefix":"39ce0c614605e81e","entry":"cdist","repo":"yzhao062/pytod","repo_kind":"official","path":"pytod/models/basic_operators.py","file_url":"https://github.com/yzhao062/pytod/blob/HEAD/pytod/models/basic_operators.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"39ce0c614605e81e"}},{"code_sha256_prefix":"e2c2517b28afc230","entry":"cdist_batch","repo":"yzhao062/pytod","repo_kind":"official","path":"pytod/models/basic_operators_batch.py","file_url":"https://github.com/yzhao062/pytod/blob/HEAD/pytod/models/basic_operators_batch.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e2c2517b28afc230"}},{"code_sha256_prefix":"56006d31259b4bb4","entry":"get_bounded_error","repo":"yzhao062/pytod","repo_kind":"official","path":"pytod/models/intermediate_layers.py","file_url":"https://github.com/yzhao062/pytod/blob/HEAD/pytod/models/intermediate_layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"56006d31259b4bb4"}},{"code_sha256_prefix":"e4b48a261460d5d7","entry":"get_bounded_error","repo":"yzhao062/pytod","repo_kind":"official","path":"pytod/models/quantization.py","file_url":"https://github.com/yzhao062/pytod/blob/HEAD/pytod/models/quantization.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"e4b48a261460d5d7"}},{"code_sha256_prefix":"6a2d330555426eca","entry":"get_cosine_similarity","repo":"yzhao062/pytod","repo_kind":"official","path":"pytod/models/abod.py","file_url":"https://github.com/yzhao062/pytod/blob/HEAD/pytod/models/abod.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"6a2d330555426eca"}},{"code_sha256_prefix":"4eacf7609ae5efbb","entry":"get_indices_clear_pairs","repo":"yzhao062/pytod","repo_kind":"official","path":"pytod/models/intermediate_layers.py","file_url":"https://github.com/yzhao062/pytod/blob/HEAD/pytod/models/intermediate_layers.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"4eacf7609ae5efbb"}},{"code_sha256_prefix":"249caf5cbdf72a39","entry":"topk","repo":"yzhao062/pytod","repo_kind":"official","path":"pytod/models/basic_operators.py","file_url":"https://github.com/yzhao062/pytod/blob/HEAD/pytod/models/basic_operators.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"249caf5cbdf72a39"}},{"code_sha256_prefix":"b4cb19e46511e58b","entry":"topk_batch","repo":"yzhao062/pytod","repo_kind":"official","path":"pytod/models/basic_operators_batch.py","file_url":"https://github.com/yzhao062/pytod/blob/HEAD/pytod/models/basic_operators_batch.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-2-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"b4cb19e46511e58b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}