{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/adversarial-sets-for-regularising-neural-link","title":"Adversarial Sets for Regularising Neural Link Predictors","arxiv_id":"1707.07596","date":"2017-07-24","proceeding":null,"authors":["Pasquale Minervini","Thomas Demeester","Tim Rocktäschel","Sebastian Riedel"],"abstract":"In adversarial training, a set of models learn together by pursuing competing\ngoals, usually defined on single data instances. However, in relational\nlearning and other non-i.i.d domains, goals can also be defined over sets of\ninstances. For example, a link predictor for the is-a relation needs to be\nconsistent with the transitivity property: if is-a(x_1, x_2) and is-a(x_2, x_3)\nhold, is-a(x_1, x_3) needs to hold as well. Here we use such assumptions for\nderiving an inconsistency loss, measuring the degree to which the model\nviolates the assumptions on an adversarially-generated set of examples. The\ntraining objective is defined as a minimax problem, where an adversary finds\nthe most offending adversarial examples by maximising the inconsistency loss,\nand the model is trained by jointly minimising a supervised loss and the\ninconsistency loss on the adversarial examples. This yields the first method\nthat can use function-free Horn clauses (as in Datalog) to regularise any\nneural link predictor, with complexity independent of the domain size. We show\nthat for several link prediction models, the optimisation problem faced by the\nadversary has efficient closed-form solutions. Experiments on link prediction\nbenchmarks indicate that given suitable prior knowledge, our method can\nsignificantly improve neural link predictors on all relevant metrics.","url_abs":"http://arxiv.org/abs/1707.07596v1","url_pdf":"http://arxiv.org/pdf/1707.07596v1.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":"adversarial-sets-for-regularising-neural-link","repo_url":"https://github.com/uclmr/inferbeddings","is_official":0,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"relational-reasoning","task_name":"Relational Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1707.07596","atlas_url":"https://app.syntology.ai/?focus=1707.07596","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"1707.07596"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1707.07596\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1707.07596"},"call":"get_concepts_for_paper(arxiv_id=\"1707.07596\")"}],"by_repo":[{"repo":"uclmr/inferbeddings","kind":"named_in_paper","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"1e9c79d7ef909f9b1a5c128f29f25bd968d18635b8a1ed359bd5803fa4a3bba7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}