{"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/analysis-of-the-impact-of-negative-sampling","title":"Analysis of the Impact of Negative Sampling on Link Prediction in Knowledge Graphs","arxiv_id":"1708.06816","date":"2017-08-22","proceeding":null,"authors":["Bhushan Kotnis","Vivi Nastase"],"abstract":"Knowledge graphs are large, useful, but incomplete knowledge repositories.\nThey encode knowledge through entities and relations which define each other\nthrough the connective structure of the graph. This has inspired methods for\nthe joint embedding of entities and relations in continuous low-dimensional\nvector spaces, that can be used to induce new edges in the graph, i.e., link\nprediction in knowledge graphs. Learning these representations relies on\ncontrasting positive instances with negative ones. Knowledge graphs include\nonly positive relation instances, leaving the door open for a variety of\nmethods for selecting negative examples. In this paper we present an empirical\nstudy on the impact of negative sampling on the learned embeddings, assessed\nthrough the task of link prediction. We use state-of-the-art knowledge graph\nembeddings -- \\rescal , TransE, DistMult and ComplEX -- and evaluate on\nbenchmark datasets -- FB15k and WN18. We compare well known methods for\nnegative sampling and additionally propose embedding based sampling methods. We\nnote a marked difference in the impact of these sampling methods on the two\ndatasets, with the \"traditional\" corrupting positives method leading to best\nresults on WN18, while embedding based methods benefiting the task on FB15k.","url_abs":"http://arxiv.org/abs/1708.06816v2","url_pdf":"http://arxiv.org/pdf/1708.06816v2.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":"analysis-of-the-impact-of-negative-sampling","repo_url":"https://github.com/bhushank/kge-rl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"knowledge-graph-embeddings","task_name":"Knowledge Graph Embeddings"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"link-prediction","task_name":"Link Prediction"}],"methods":[{"method_slug":"transe","method_name":"TransE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1708.06816","atlas_url":"https://app.syntology.ai/?focus=1708.06816","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":"1708.06816"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1708.06816\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1708.06816"},"call":"get_concepts_for_paper(arxiv_id=\"1708.06816\")"}],"by_repo":[{"repo":"bhushank/kge-rl","kind":"official","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":"30d1f4e0b2961d2e53ddff0e92ca3545adab5d4048313d18bc8c3d28eab54396","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}