{"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/link-and-code-fast-indexing-with-graphs-and","title":"Link and code: Fast indexing with graphs and compact regression codes","arxiv_id":"1804.09996","date":"2018-04-26","proceeding":"CVPR 2018 6","authors":["Matthijs Douze","Alexandre Sablayrolles","Hervé Jégou"],"abstract":"Similarity search approaches based on graph walks have recently attained\noutstanding speed-accuracy trade-offs, taking aside the memory requirements. In\nthis paper, we revisit these approaches by considering, additionally, the\nmemory constraint required to index billions of images on a single server. This\nleads us to propose a method based both on graph traversal and compact\nrepresentations. We encode the indexed vectors using quantization and exploit\nthe graph structure to refine the similarity estimation.\n  In essence, our method takes the best of these two worlds: the search\nstrategy is based on nested graphs, thereby providing high precision with a\nrelatively small set of comparisons. At the same time it offers a significant\nmemory compression. As a result, our approach outperforms the state of the art\non operating points considering 64-128 bytes per vector, as demonstrated by our\nresults on two billion-scale public benchmarks.","url_abs":"http://arxiv.org/abs/1804.09996v2","url_pdf":"http://arxiv.org/pdf/1804.09996v2.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":"link-and-code-fast-indexing-with-graphs-and","repo_url":"https://github.com/facebookresearch/faiss","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"link-and-code-fast-indexing-with-graphs-and","repo_url":"https://github.com/NGDSystems/faiss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"link-and-code-fast-indexing-with-graphs-and","repo_url":"https://github.com/NJU-yasuo/faiss_t","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"link-and-code-fast-indexing-with-graphs-and","repo_url":"https://github.com/PhilipBAdams/faiss-learned-termination-prior-weighted","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"link-and-code-fast-indexing-with-graphs-and","repo_url":"https://github.com/architecture-research-group/ae-asplo25-iks-faiss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"link-and-code-fast-indexing-with-graphs-and","repo_url":"https://github.com/gauenk/faiss_fork","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"link-and-code-fast-indexing-with-graphs-and","repo_url":"https://github.com/hartb/faiss-gpu-feedstock","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"link-and-code-fast-indexing-with-graphs-and","repo_url":"https://github.com/junjya/faiss","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"image-similarity-search","task_name":"Image Similarity Search"},{"task_slug":"quantization","task_name":"Quantization"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1804.09996","atlas_url":"https://app.syntology.ai/?focus=1804.09996","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":"1804.09996"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1804.09996\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1804.09996"},"call":"get_concepts_for_paper(arxiv_id=\"1804.09996\")"}],"by_repo":[{"repo":"facebookresearch/faiss","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":3,"harvested_for":["1609.01882","1702.08734","2606.04522"],"harvested_for_calls":[{"arxiv_id":"1609.01882","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1609.01882"},"call":"get_harvested_code_for_paper(arxiv_id=\"1609.01882\")"},{"arxiv_id":"1702.08734","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1702.08734"},"call":"get_harvested_code_for_paper(arxiv_id=\"1702.08734\")"},{"arxiv_id":"2606.04522","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2606.04522"},"call":"get_harvested_code_for_paper(arxiv_id=\"2606.04522\")"}]},{"repo":"NGDSystems/faiss","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1702.08734"],"harvested_for_calls":[{"arxiv_id":"1702.08734","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1702.08734"},"call":"get_harvested_code_for_paper(arxiv_id=\"1702.08734\")"}]},{"repo":"NJU-yasuo/faiss_t","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"PhilipBAdams/faiss-learned-termination-prior-weighted","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1702.08734"],"harvested_for_calls":[{"arxiv_id":"1702.08734","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1702.08734"},"call":"get_harvested_code_for_paper(arxiv_id=\"1702.08734\")"}]},{"repo":"architecture-research-group/ae-asplo25-iks-faiss","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1702.08734"],"harvested_for_calls":[{"arxiv_id":"1702.08734","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1702.08734"},"call":"get_harvested_code_for_paper(arxiv_id=\"1702.08734\")"}]},{"repo":"gauenk/faiss_fork","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1702.08734"],"harvested_for_calls":[{"arxiv_id":"1702.08734","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1702.08734"},"call":"get_harvested_code_for_paper(arxiv_id=\"1702.08734\")"}]},{"repo":"hartb/faiss-gpu-feedstock","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"junjya/faiss","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1702.08734"],"harvested_for_calls":[{"arxiv_id":"1702.08734","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1702.08734"},"call":"get_harvested_code_for_paper(arxiv_id=\"1702.08734\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"03f67cf5f3d5dd3db88dde216b0505a1927359a147eff569b14385c91c6ce9bc","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}