{"url":"/task/graph-matching","name":"Graph Matching","slug":"graph-matching","description_markdown":"**Graph Matching** is the problem of finding correspondences between two sets of vertices while preserving complex relational information among them. Since the graph structure has a strong capacity to represent objects and robustness to severe deformation and outliers, it is frequently adopted to formulate various correspondence problems in the field of computer vision. Theoretically, the Graph Matching problem can be solved by exhaustively searching the entire solution space. However, this approach is infeasible in practice because the solution space expands exponentially as the size of input data increases. For that reason, previous studies have attempted to solve the problem by using various approximation techniques.\n\n\n<span class=\"description-source\">Source: [Consistent Multiple Graph Matching with Multi-layer Random Walks Synchronization ](https://arxiv.org/abs/1712.02575)</span>","categories":[{"name":"Graphs","url":"/area/graphs"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":477,"papers_with_code":163,"benchmarks":7,"benchmark_tables_in_archive":7,"benchmark_tables_shown":7,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":11,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/graph-matching-on-pascal-voc","slug":"graph-matching-on-pascal-voc","dataset":"PASCAL VOC","dataset_url":"/dataset/pascal-voc","rows_in_archive":31,"metrics":["F1 score","matching accuracy"],"first_row_in_archive_order":{"model":"URL","paper_title":"Universe Points Representation Learning for Partial Multi-Graph Matching","paper_url":"/paper/universe-points-representation-learning-for","paper_date":"2022-12-01","arxiv_id":"2212.00780","code_links":[],"syntology":null}},{"leaderboard":"/sota/graph-matching-on-willow-object-class","slug":"graph-matching-on-willow-object-class","dataset":"Willow Object Class","dataset_url":null,"rows_in_archive":23,"metrics":["matching accuracy","F1 score"],"first_row_in_archive_order":{"model":"COMMON","paper_title":"Graph Matching with Bi-level Noisy Correspondence","paper_url":"/paper/graph-matching-with-bi-level-noisy","paper_date":"2022-12-08","arxiv_id":"2212.04085","code_links":[{"title":"Thinklab-SJTU/ThinkMatch","url":"https://github.com/Thinklab-SJTU/ThinkMatch"},{"title":"Lin-Yijie/Graph-Matching-Networks","url":"https://github.com/Lin-Yijie/Graph-Matching-Networks/tree/main/COMMON"},{"title":"xlearning-scu/2023-iccv-common","url":"https://github.com/xlearning-scu/2023-iccv-common"}],"syntology":{"n":7,"n_ran":7,"n_unverified":0,"n_pointer_only":7}}},{"leaderboard":"/sota/graph-matching-on-spair-71k","slug":"graph-matching-on-spair-71k","dataset":"SPair-71k","dataset_url":"/dataset/spair-71k","rows_in_archive":8,"metrics":["matching accuracy"],"first_row_in_archive_order":{"model":"CREAM","paper_title":"Cross-modal Retrieval with Noisy Correspondence via Consistency Refining and Mining","paper_url":"/paper/cross-modal-retrieval-with-noisy","paper_date":"2024-03-25","arxiv_id":null,"code_links":[{"title":"XLearning-SCU/2024-TIP-CREAM","url":"https://github.com/XLearning-SCU/2024-TIP-CREAM"}],"syntology":null}},{"leaderboard":"/sota/graph-matching-on-imcpt-sparsegm-100","slug":"graph-matching-on-imcpt-sparsegm-100","dataset":"IMCPT-SparseGM-100","dataset_url":"/dataset/imcpt-sparsegm-100","rows_in_archive":6,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"GCAN-AFAT-U","paper_title":"Deep Learning of Partial Graph Matching via Differentiable Top-K","paper_url":"/paper/deep-learning-of-partial-graph-matching-via","paper_date":"2023-01-01","arxiv_id":null,"code_links":[{"title":"Thinklab-SJTU/ThinkMatch","url":"https://github.com/Thinklab-SJTU/ThinkMatch"}],"syntology":null}},{"leaderboard":"/sota/graph-matching-on-imcpt-sparsegm-50","slug":"graph-matching-on-imcpt-sparsegm-50","dataset":"IMCPT-SparseGM-50","dataset_url":"/dataset/imcpt-sparsegm","rows_in_archive":6,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"GCAN-AFAT-I","paper_title":"Deep Learning of Partial Graph Matching via Differentiable Top-K","paper_url":"/paper/deep-learning-of-partial-graph-matching-via","paper_date":"2023-01-01","arxiv_id":null,"code_links":[{"title":"Thinklab-SJTU/ThinkMatch","url":"https://github.com/Thinklab-SJTU/ThinkMatch"}],"syntology":null}},{"leaderboard":"/sota/graph-matching-on-rare","slug":"graph-matching-on-rare","dataset":"RARE","dataset_url":"/dataset/rare","rows_in_archive":5,"metrics":["Spearman Correlation"],"first_row_in_archive_order":{"model":"Smatch","paper_title":"Smatch: an Evaluation Metric for Semantic Feature Structures","paper_url":"/paper/smatch-an-evaluation-metric-for-semantic","paper_date":"2013-08-01","arxiv_id":null,"code_links":[{"title":"snowblink14/smatch","url":"https://github.com/snowblink14/smatch"}],"syntology":null}},{"leaderboard":"/sota/graph-matching-on-cub","slug":"graph-matching-on-cub","dataset":"CUB","dataset_url":"/dataset/cub-200-2011","rows_in_archive":4,"metrics":["F1 score"],"first_row_in_archive_order":{"model":"URL","paper_title":"Universe Points Representation Learning for Partial Multi-Graph Matching","paper_url":"/paper/universe-points-representation-learning-for","paper_date":"2022-12-01","arxiv_id":"2212.00780","code_links":[],"syntology":null}}],"datasets":[{"url":"/dataset/cub-200-2011","name":"CUB-200-2011","full_name":"Caltech-UCSD Birds-200-2011","num_papers_in_archive":2235},{"url":"/dataset/pascal-voc","name":"PASCAL VOC","full_name":"PASCAL Visual Object Classes Challenge","num_papers_in_archive":198},{"url":"/dataset/spair-71k","name":"SPair-71k","full_name":"","num_papers_in_archive":71},{"url":"/dataset/occluded-reid","name":"Occluded REID","full_name":"Occluded REID","num_papers_in_archive":65},{"url":"/dataset/birdsong","name":"BirdSong","full_name":"","num_papers_in_archive":35},{"url":"/dataset/linux","name":"Linux","full_name":"Linux Program Dependence Graphs","num_papers_in_archive":14},{"url":"/dataset/mindboggle","name":"Mindboggle","full_name":"","num_papers_in_archive":9},{"url":"/dataset/rare","name":"RARE","full_name":"Randomized AMRs with Rewired Edges","num_papers_in_archive":5},{"url":"/dataset/dispscenes","name":"DispScenes","full_name":null,"num_papers_in_archive":2},{"url":"/dataset/imcpt-sparsegm-100","name":"IMCPT-SparseGM-100","full_name":"","num_papers_in_archive":1},{"url":"/dataset/imcpt-sparsegm","name":"IMCPT-SparseGM-50","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":163,"tagged_in_all":477,"items":[{"url":"/paper/molgan-an-implicit-generative-model-for-small","title":"MolGAN: An implicit generative model for small molecular graphs","date":"2018-05-30","arxiv_id":"1805.11973","repositories_listed":11,"syntology":{"n":17,"n_ran":3,"n_unverified":14,"n_pointer_only":1}},{"url":"/paper/graph2vec-learning-distributed","title":"graph2vec: Learning Distributed Representations of Graphs","date":"2017-07-17","arxiv_id":"1707.05005","repositories_listed":6,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/deep-graph-matching-via-blackbox","title":"Deep Graph Matching via Blackbox Differentiation of Combinatorial Solvers","date":"2020-03-25","arxiv_id":"2003.11657","repositories_listed":5,"syntology":{"n":11,"n_ran":5,"n_unverified":6,"n_pointer_only":3}},{"url":"/paper/graphecho-graph-driven-unsupervised-domain","title":"GraphEcho: Graph-Driven Unsupervised Domain Adaptation for Echocardiogram Video Segmentation","date":"2023-09-20","arxiv_id":"2309.11145","repositories_listed":4,"syntology":null},{"url":"/paper/multiple-heads-are-better-than-one-few-shot","title":"Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts","date":"2021-04-02","arxiv_id":"2104.00887","repositories_listed":4,"syntology":null},{"url":"/paper/pharmaconet-accelerating-structure-based","title":"PharmacoNet: Accelerating Large-Scale Virtual Screening by Deep Pharmacophore Modeling","date":"2023-10-01","arxiv_id":"2310.00681","repositories_listed":3,"syntology":{"n":8,"n_ran":8,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/graph-matching-with-bi-level-noisy","title":"Graph Matching with Bi-level Noisy Correspondence","date":"2022-12-08","arxiv_id":"2212.04085","repositories_listed":3,"syntology":{"n":7,"n_ran":7,"n_unverified":0,"n_pointer_only":7}},{"url":"/paper/semantic-histogram-based-graph-matching-for","title":"Semantic Histogram Based Graph Matching for Real-Time Multi-Robot Global Localization in Large Scale Environment","date":"2020-10-19","arxiv_id":"2010.09297","repositories_listed":3,"syntology":null},{"url":"/paper/amr-similarity-metrics-from-principles","title":"AMR Similarity Metrics from Principles","date":"2020-01-29","arxiv_id":"2001.10929","repositories_listed":3,"syntology":null},{"url":"/paper/dynamic-graph-representation-for-partially","title":"Dynamic Graph Representation for Partially Occluded Biometrics","date":"2019-12-01","arxiv_id":"1912.00377","repositories_listed":3,"syntology":null},{"url":"/paper/graph-matching-networks-for-learning-the-1","title":"Graph Matching Networks for Learning the Similarity of Graph Structured Objects","date":"2019-04-29","arxiv_id":"1904.12787","repositories_listed":3,"syntology":null},{"url":"/paper/multiscale-dynamic-graph-representation-for","title":"Multiscale Dynamic Graph Representation for Biometric Recognition with Occlusions","date":"2023-07-27","arxiv_id":"2307.14617","repositories_listed":2,"syntology":null},{"url":"/paper/unsupervised-manifold-alignment-with-joint","title":"Unsupervised Manifold Alignment with Joint Multidimensional Scaling","date":"2022-07-06","arxiv_id":"2207.02968","repositories_listed":2,"syntology":{"n":17,"n_ran":14,"n_unverified":3,"n_pointer_only":16}},{"url":"/paper/a-comparative-study-of-graph-matching","title":"A Comparative Study of Graph Matching Algorithms in Computer Vision","date":"2022-07-01","arxiv_id":"2207.00291","repositories_listed":2,"syntology":{"n":22,"n_ran":1,"n_unverified":21,"n_pointer_only":0}},{"url":"/paper/gradient-backpropagation-through","title":"Backpropagation through Combinatorial Algorithms: Identity with Projection Works","date":"2022-05-30","arxiv_id":"2205.15213","repositories_listed":2,"syntology":null},{"url":"/paper/graph-neural-networks-for-cross-camera-data","title":"Graph Neural Networks for Cross-Camera Data Association","date":"2022-01-17","arxiv_id":"2201.06311","repositories_listed":2,"syntology":null},{"url":"/paper/joint-graph-learning-and-matching-for","title":"Joint Graph Learning and Matching for Semantic Feature Correspondence","date":"2021-09-01","arxiv_id":"2109.00240","repositories_listed":2,"syntology":null},{"url":"/paper/adaptive-edge-attention-for-graph-matching","title":"Adaptive Edge Attention for Graph Matching with Outliers","date":"2021-08-19","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/deep-graph-matching-meets-mixed-integer","title":"Deep graph matching meets mixed-integer linear programming: Relax at your own risk ?","date":"2021-08-01","arxiv_id":"2108.00394","repositories_listed":2,"syntology":null},{"url":"/paper/robust-point-cloud-registration-framework","title":"Robust Point Cloud Registration Framework Based on Deep Graph Matching","date":"2021-03-07","arxiv_id":"2103.04256","repositories_listed":2,"syntology":{"n":38,"n_ran":25,"n_unverified":13,"n_pointer_only":38}},{"url":"/paper/fusion-moves-for-graph-matching","title":"Fusion Moves for Graph Matching","date":"2021-01-28","arxiv_id":"2101.12085","repositories_listed":2,"syntology":null},{"url":"/paper/deep-reinforcement-learning-of-graph-matching","title":"Revocable Deep Reinforcement Learning with Affinity Regularization for Outlier-Robust Graph Matching","date":"2020-12-16","arxiv_id":"2012.08950","repositories_listed":2,"syntology":{"n":8,"n_ran":7,"n_unverified":1,"n_pointer_only":8}},{"url":"/paper/high-order-information-matters-learning","title":"High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification","date":"2020-03-18","arxiv_id":"2003.08177","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/deep-graph-matching-consensus-1","title":"Deep Graph Matching Consensus","date":"2020-01-27","arxiv_id":"2001.09621","repositories_listed":2,"syntology":null},{"url":"/paper/learning-cross-modal-context-graph-for-visual-1","title":"Learning Cross-modal Context Graph for Visual Grounding","date":"2019-11-20","arxiv_id":"1911.09042","repositories_listed":2,"syntology":null},{"url":"/paper/mtab-matching-tabular-data-to-knowledge-graph","title":"MTab: Matching Tabular Data to Knowledge Graph using Probability Models","date":"2019-10-01","arxiv_id":"1910.00246","repositories_listed":2,"syntology":null},{"url":"/paper/isonn-isomorphic-neural-network-for-graph","title":"IsoNN: Isomorphic Neural Network for Graph Representation Learning and Classification","date":"2019-07-22","arxiv_id":"1907.09495","repositories_listed":2,"syntology":null},{"url":"/paper/sembleu-a-robust-metric-for-amr-parsing","title":"SemBleu: A Robust Metric for AMR Parsing Evaluation","date":"2019-05-26","arxiv_id":"1905.10726","repositories_listed":2,"syntology":null},{"url":"/paper/sosnet-second-order-similarity-regularization","title":"SOSNet: Second Order Similarity Regularization for Local Descriptor Learning","date":"2019-04-10","arxiv_id":"1904.05019","repositories_listed":2,"syntology":null},{"url":"/paper/gromov-wasserstein-learning-for-graph","title":"Gromov-Wasserstein Learning for Graph Matching and Node Embedding","date":"2019-01-17","arxiv_id":"1901.06003","repositories_listed":2,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":2}}],"syntology_records":11,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}