{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/improving-local-identifiability-in","title":"Improving Local Identifiability in Probabilistic Box Embeddings","arxiv_id":"2010.04831","date":"2020-10-09","proceeding":"NeurIPS 2020 12","authors":["Shib Sankar Dasgupta","Michael Boratko","Dongxu Zhang","Luke Vilnis","Xiang Lorraine Li","Andrew McCallum"],"abstract":"Geometric embeddings have recently received attention for their natural ability to represent transitive asymmetric relations via containment. Box embeddings, where objects are represented by n-dimensional hyperrectangles, are a particularly promising example of such an embedding as they are closed under intersection and their volume can be calculated easily, allowing them to naturally represent calibrated probability distributions. The benefits of geometric embeddings also introduce a problem of local identifiability, however, where whole neighborhoods of parameters result in equivalent loss which impedes learning. Prior work addressed some of these issues by using an approximation to Gaussian convolution over the box parameters, however, this intersection operation also increases the sparsity of the gradient. In this work, we model the box parameters with min and max Gumbel distributions, which were chosen such that space is still closed under the operation of the intersection. The calculation of the expected intersection volume involves all parameters, and we demonstrate experimentally that this drastically improves the ability of such models to learn.","url_abs":"https://arxiv.org/abs/2010.04831v2","url_pdf":"https://arxiv.org/pdf/2010.04831v2.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":"improving-local-identifiability-in","repo_url":"https://github.com/iesl/geometric_graph_embedding","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[],"methods":[{"method_slug":"convolution","method_name":"Convolution"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2010.04831","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.04831"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/iesl/geometric_graph_embedding","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":9},"by_repo_kind":{"listed":{"samples":9,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"74b56dee8af9c94d","entry":"convert_to_outtree","repo":"iesl/geometric_graph_embedding","repo_kind":"listed","path":"src/graph_modeling/generate/generic.py","file_url":"https://github.com/iesl/geometric_graph_embedding/blob/HEAD/src/graph_modeling/generate/generic.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"74b56dee8af9c94d"}},{"code_sha256_prefix":"ead45e312b908abd","entry":"from_linkage_matrix","repo":"iesl/geometric_graph_embedding","repo_kind":"listed","path":"src/graph_modeling/generate/hac.py","file_url":"https://github.com/iesl/geometric_graph_embedding/blob/HEAD/src/graph_modeling/generate/hac.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ead45e312b908abd"}},{"code_sha256_prefix":"32e8c69cc44844db","entry":"generate","repo":"iesl/geometric_graph_embedding","repo_kind":"listed","path":"src/graph_modeling/generate/hac.py","file_url":"https://github.com/iesl/geometric_graph_embedding/blob/HEAD/src/graph_modeling/generate/hac.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"32e8c69cc44844db"}},{"code_sha256_prefix":"6b17a38b61efff88","entry":"generate","repo":"iesl/geometric_graph_embedding","repo_kind":"listed","path":"src/graph_modeling/generate/knn_graph.py","file_url":"https://github.com/iesl/geometric_graph_embedding/blob/HEAD/src/graph_modeling/generate/knn_graph.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6b17a38b61efff88"}},{"code_sha256_prefix":"9c877d5a9cfe2a1d","entry":"generate","repo":"iesl/geometric_graph_embedding","repo_kind":"listed","path":"src/graph_modeling/generate/kronecker_graph.py","file_url":"https://github.com/iesl/geometric_graph_embedding/blob/HEAD/src/graph_modeling/generate/kronecker_graph.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9c877d5a9cfe2a1d"}},{"code_sha256_prefix":"3e86800f7a81f156","entry":"generate","repo":"iesl/geometric_graph_embedding","repo_kind":"listed","path":"src/graph_modeling/generate/price.py","file_url":"https://github.com/iesl/geometric_graph_embedding/blob/HEAD/src/graph_modeling/generate/price.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3e86800f7a81f156"}},{"code_sha256_prefix":"dc0c718b09c9a0c8","entry":"generate","repo":"iesl/geometric_graph_embedding","repo_kind":"listed","path":"src/graph_modeling/generate/random_tree.py","file_url":"https://github.com/iesl/geometric_graph_embedding/blob/HEAD/src/graph_modeling/generate/random_tree.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dc0c718b09c9a0c8"}},{"code_sha256_prefix":"f09239998b1749d1","entry":"load_text","repo":"iesl/geometric_graph_embedding","repo_kind":"listed","path":"src/graph_modeling/generate/hac.py","file_url":"https://github.com/iesl/geometric_graph_embedding/blob/HEAD/src/graph_modeling/generate/hac.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f09239998b1749d1"}},{"code_sha256_prefix":"30dc892e2be52489","entry":"remove_self_loops","repo":"iesl/geometric_graph_embedding","repo_kind":"listed","path":"src/graph_modeling/generate/generic.py","file_url":"https://github.com/iesl/geometric_graph_embedding/blob/HEAD/src/graph_modeling/generate/generic.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"30dc892e2be52489"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}