{"url":"/task/relational-reasoning","name":"Relational Reasoning","slug":"relational-reasoning","description_markdown":"The goal of **Relational Reasoning** is to figure out the relationships among different entities, such as image pixels, words or sentences, human skeletons or interactive moving agents.\n\n\n<span class=\"description-source\">Source: [Social-WaGDAT: Interaction-aware Trajectory Prediction via Wasserstein Graph Double-Attention Network ](https://arxiv.org/abs/2002.06241)</span>","categories":[{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":483,"papers_with_code":179,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":12,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/relational-reasoning-on-clutrr","slug":"relational-reasoning-on-clutrr","dataset":"CLUTRR (k=3)","dataset_url":null,"rows_in_archive":1,"metrics":["4 Hops","5 Hops","6 Hops","7 Hops","8 Hops","9 Hops","10 Hops"],"first_row_in_archive_order":{"model":"CTP A","paper_title":"Learning Reasoning Strategies in End-to-End Differentiable Proving","paper_url":"/paper/learning-reasoning-strategies-in-end-to-end","paper_date":"2020-07-13","arxiv_id":"2007.06477","code_links":[{"title":"facebookresearch/clutrr","url":"https://github.com/facebookresearch/clutrr"},{"title":"uclnlp/ctp","url":"https://github.com/uclnlp/ctp"}],"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/webkb","name":"WebKB","full_name":"WebKB","num_papers_in_archive":113},{"url":"/dataset/raven","name":"RAVEN","full_name":"","num_papers_in_archive":96},{"url":"/dataset/abstractreasoning","name":"AbstractReasoning","full_name":"AbstractReasoning","num_papers_in_archive":86},{"url":"/dataset/pgm","name":"PGM","full_name":"Procedurally Generated Matrices (PGM)","num_papers_in_archive":57},{"url":"/dataset/pisc","name":"PISC","full_name":"People in Social Context","num_papers_in_archive":13},{"url":"/dataset/raven-fair","name":"RAVEN-FAIR","full_name":null,"num_papers_in_archive":9},{"url":"/dataset/spartqa-1","name":"SPARTQA -","full_name":"SPAtial Reasoning on Textual Question Answering.","num_papers_in_archive":9},{"url":"/dataset/machine-number-sense","name":"Machine Number Sense","full_name":"","num_papers_in_archive":2},{"url":"/dataset/sequence-consistency-evaluation-sce-tests","name":"Sequence Consistency Evaluation (SCE) tests","full_name":"","num_papers_in_archive":1},{"url":"/dataset/texrel","name":"TexRel","full_name":"","num_papers_in_archive":1},{"url":"/dataset/wikidatasets","name":"WikiDataSets","full_name":"","num_papers_in_archive":1},{"url":"/dataset/cvr-tasks","name":"Compositional Visual Reasoning (CVR)","full_name":"","num_papers_in_archive":0}],"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":179,"tagged_in_all":483,"items":[{"url":"/paper/relational-inductive-biases-deep-learning-and","title":"Relational inductive biases, deep learning, and graph networks","date":"2018-06-04","arxiv_id":"1806.01261","repositories_listed":31,"syntology":{"n":51,"n_ran":13,"n_unverified":38,"n_pointer_only":15}},{"url":"/paper/a-simple-neural-network-module-for-relational","title":"A simple neural network module for relational reasoning","date":"2017-06-05","arxiv_id":"1706.01427","repositories_listed":20,"syntology":{"n":7,"n_ran":3,"n_unverified":4,"n_pointer_only":1}},{"url":"/paper/inductive-relation-prediction-on-knowledge","title":"Inductive Relation Prediction by Subgraph Reasoning","date":"2019-11-16","arxiv_id":"1911.06962","repositories_listed":10,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/graph-based-global-reasoning-networks","title":"Graph-Based Global Reasoning Networks","date":"2018-11-30","arxiv_id":"1811.12814","repositories_listed":9,"syntology":{"n":15,"n_ran":8,"n_unverified":7,"n_pointer_only":4}},{"url":"/paper/complex-embeddings-for-simple-link-prediction","title":"Complex Embeddings for Simple Link Prediction","date":"2016-06-20","arxiv_id":"1606.06357","repositories_listed":9,"syntology":null},{"url":"/paper/relational-deep-reinforcement-learning","title":"Relational Deep Reinforcement Learning","date":"2018-06-05","arxiv_id":"1806.01830","repositories_listed":7,"syntology":{"n":8,"n_ran":4,"n_unverified":4,"n_pointer_only":4}},{"url":"/paper/fast-graph-representation-learning-with","title":"Fast Graph Representation Learning with PyTorch Geometric","date":"2019-03-06","arxiv_id":"1903.02428","repositories_listed":6,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/recurrent-relational-networks","title":"Recurrent Relational Networks","date":"2017-11-21","arxiv_id":"1711.08028","repositories_listed":6,"syntology":null},{"url":"/paper/clutrr-a-diagnostic-benchmark-for-inductive","title":"CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text","date":"2019-08-16","arxiv_id":"1908.06177","repositories_listed":5,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/temporal-relational-reasoning-in-videos","title":"Temporal Relational Reasoning in Videos","date":"2017-11-22","arxiv_id":"1711.08496","repositories_listed":5,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/your-diffusion-model-is-secretly-a-zero-shot","title":"Your Diffusion Model is Secretly a Zero-Shot Classifier","date":"2023-03-28","arxiv_id":"2303.16203","repositories_listed":4,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/holographic-embeddings-of-knowledge-graphs","title":"Holographic Embeddings of Knowledge Graphs","date":"2015-10-16","arxiv_id":"1510.04935","repositories_listed":4,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/rlipv2-fast-scaling-of-relational-language","title":"RLIPv2: Fast Scaling of Relational Language-Image Pre-training","date":"2023-08-18","arxiv_id":"2308.09351","repositories_listed":3,"syntology":{"n":30,"n_ran":22,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/an-insect-inspired-randomly-weighted-neural","title":"An Insect-Inspired Randomly, Weighted Neural Network with Random Fourier Features For Neuro-Symbolic Relational Learning","date":"2021-09-11","arxiv_id":"2109.06663","repositories_listed":3,"syntology":null},{"url":"/paper/learning-from-protein-structure-with","title":"Learning from Protein Structure with Geometric Vector Perceptrons","date":"2020-09-03","arxiv_id":"2009.01411","repositories_listed":3,"syntology":{"n":6,"n_ran":5,"n_unverified":1,"n_pointer_only":6}},{"url":"/paper/generative-3d-part-assembly-via-dynamic-graph","title":"Generative 3D Part Assembly via Dynamic Graph Learning","date":"2020-06-14","arxiv_id":"2006.07793","repositories_listed":3,"syntology":null},{"url":"/paper/commongen-a-constrained-text-generation","title":"CommonGen: A Constrained Text Generation Challenge for Generative Commonsense Reasoning","date":"2019-11-09","arxiv_id":"1911.03705","repositories_listed":3,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/disentangling-and-integrating-relational-and","title":"Disentangling and Integrating Relational and Sensory Information in Transformer Architectures","date":"2024-05-26","arxiv_id":"2405.16727","repositories_listed":2,"syntology":{"n":21,"n_ran":14,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/mlps-learn-in-context","title":"MLPs Learn In-Context on Regression and Classification Tasks","date":"2024-05-24","arxiv_id":"2405.15618","repositories_listed":2,"syntology":{"n":16,"n_ran":2,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/visual-causal-scene-refinement-for-video","title":"Visual Causal Scene Refinement for Video Question Answering","date":"2023-05-07","arxiv_id":"2305.04224","repositories_listed":2,"syntology":null},{"url":"/paper/cross-modal-causal-relational-reasoning-for","title":"Cross-Modal Causal Relational Reasoning for Event-Level Visual Question Answering","date":"2022-07-26","arxiv_id":"2207.12647","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/global-reasoned-multi-task-learning-model-for","title":"Global-Reasoned Multi-Task Learning Model for Surgical Scene Understanding","date":"2022-01-28","arxiv_id":"2201.11957","repositories_listed":2,"syntology":{"n":8,"n_ran":1,"n_unverified":7,"n_pointer_only":8}},{"url":"/paper/representing-prior-knowledge-using-randomly","title":"Representing Prior Knowledge Using Randomly, Weighted Feature Networks for Visual Relationship Detection","date":"2021-11-20","arxiv_id":"2111.10686","repositories_listed":2,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/rrnet-relational-reasoning-network-with","title":"RRNet: Relational Reasoning Network with Parallel Multi-scale Attention for Salient Object Detection in Optical Remote Sensing Images","date":"2021-10-27","arxiv_id":"2110.14223","repositories_listed":2,"syntology":null},{"url":"/paper/automatic-generation-of-contrast-sets-from","title":"Automatic Generation of Contrast Sets from Scene Graphs: Probing the Compositional Consistency of GQA","date":"2021-03-17","arxiv_id":"2103.09591","repositories_listed":2,"syntology":{"n":5,"n_ran":1,"n_unverified":4,"n_pointer_only":5}},{"url":"/paper/logic-tensor-networks","title":"Logic Tensor Networks","date":"2020-12-25","arxiv_id":"2012.13635","repositories_listed":2,"syntology":null},{"url":"/paper/fusing-context-into-knowledge-graph-for","title":"Fusing Context Into Knowledge Graph for Commonsense Question Answering","date":"2020-12-09","arxiv_id":"2012.04808","repositories_listed":2,"syntology":null},{"url":"/paper/scale-localized-abstract-reasoning","title":"Scale-Localized Abstract Reasoning","date":"2020-09-20","arxiv_id":"2009.09405","repositories_listed":2,"syntology":{"n":17,"n_ran":2,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/uncertainty-based-traffic-accident","title":"Uncertainty-based Traffic Accident Anticipation with Spatio-Temporal Relational Learning","date":"2020-08-01","arxiv_id":"2008.00334","repositories_listed":2,"syntology":{"n":10,"n_ran":1,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/learning-reasoning-strategies-in-end-to-end","title":"Learning Reasoning Strategies in End-to-End Differentiable Proving","date":"2020-07-13","arxiv_id":"2007.06477","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}}],"syntology_records":22,"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"}}