{"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/apex-2-adaptive-and-extreme-summarization-for","title":"APEX$^2$: Adaptive and Extreme Summarization for Personalized Knowledge Graphs","arxiv_id":"2412.17336","date":"2024-12-23","proceeding":null,"authors":["Zihao Li","Dongqi Fu","Mengting Ai","Jingrui He"],"abstract":"Knowledge graphs (KGs), which store an extensive number of relational facts, serve various applications. Recently, personalized knowledge graphs (PKGs) have emerged as a solution to optimize storage costs by customizing their content to align with users' specific interests within particular domains. In the real world, on one hand, user queries and their underlying interests are inherently evolving, requiring PKGs to adapt continuously; on the other hand, the summarization is constantly expected to be as small as possible in terms of storage cost. However, the existing PKG summarization methods implicitly assume that the user's interests are constant and do not shift. Furthermore, when the size constraint of PKG is extremely small, the existing methods cannot distinguish which facts are more of immediate interest and guarantee the utility of the summarized PKG. To address these limitations, we propose APEX$^2$, a highly scalable PKG summarization framework designed with robust theoretical guarantees to excel in adaptive summarization tasks with extremely small size constraints. To be specific, after constructing an initial PKG, APEX$^2$ continuously tracks the interest shift and adjusts the previous summary. We evaluate APEX$^2$ under an evolving query setting on benchmark KGs containing up to 12 million triples, summarizing with compression ratios $\\leq 0.1\\%$. The experiments show that APEX outperforms state-of-the-art baselines in terms of both query-answering accuracy and efficiency.","url_abs":"https://arxiv.org/abs/2412.17336v1","url_pdf":"https://arxiv.org/pdf/2412.17336v1.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":"apex-2-adaptive-and-extreme-summarization-for","repo_url":"https://github.com/iDEA-iSAIL-Lab-UIUC/APEX","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"extreme-summarization","task_name":"Extreme Summarization"},{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"}],"methods":[{"method_slug":"align","method_name":"ALIGN"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2412.17336","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.17336"}},"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/iDEA-iSAIL-Lab-UIUC/APEX","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":15},"by_repo_kind":{"official":{"samples":15,"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":"c46f6030afeae60b","entry":"Heat_Diffuse","repo":"iDEA-iSAIL-Lab-UIUC/APEX","repo_kind":"official","path":"code/src/apex.py","file_url":"https://github.com/iDEA-iSAIL-Lab-UIUC/APEX/blob/HEAD/code/src/apex.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c46f6030afeae60b"}},{"code_sha256_prefix":"bbaecb13e64ffcd6","entry":"binary_find","repo":"iDEA-iSAIL-Lab-UIUC/APEX","repo_kind":"official","path":"code/src/apex.py","file_url":"https://github.com/iDEA-iSAIL-Lab-UIUC/APEX/blob/HEAD/code/src/apex.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bbaecb13e64ffcd6"}},{"code_sha256_prefix":"472c5d90fd377046","entry":"check_question","repo":"iDEA-iSAIL-Lab-UIUC/APEX","repo_kind":"official","path":"code/src/query.py","file_url":"https://github.com/iDEA-iSAIL-Lab-UIUC/APEX/blob/HEAD/code/src/query.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"472c5d90fd377046"}},{"code_sha256_prefix":"d19410e1bd194547","entry":"entity_counts","repo":"iDEA-iSAIL-Lab-UIUC/APEX","repo_kind":"official","path":"code/src/user.py","file_url":"https://github.com/iDEA-iSAIL-Lab-UIUC/APEX/blob/HEAD/code/src/user.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"d19410e1bd194547"}},{"code_sha256_prefix":"1de880067d0e1282","entry":"f1_score","repo":"iDEA-iSAIL-Lab-UIUC/APEX","repo_kind":"official","path":"code/src/metrics.py","file_url":"https://github.com/iDEA-iSAIL-Lab-UIUC/APEX/blob/HEAD/code/src/metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1de880067d0e1282"}},{"code_sha256_prefix":"5c179350b6071ab6","entry":"float_in_zero_one","repo":"iDEA-iSAIL-Lab-UIUC/APEX","repo_kind":"official","path":"PKG_EXP/MetaQA/generate_query.py","file_url":"https://github.com/iDEA-iSAIL-Lab-UIUC/APEX/blob/HEAD/PKG_EXP/MetaQA/generate_query.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5c179350b6071ab6"}},{"code_sha256_prefix":"9b37cc76dbd1df80","entry":"load_question","repo":"iDEA-iSAIL-Lab-UIUC/APEX","repo_kind":"official","path":"code/src/query.py","file_url":"https://github.com/iDEA-iSAIL-Lab-UIUC/APEX/blob/HEAD/code/src/query.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9b37cc76dbd1df80"}},{"code_sha256_prefix":"51df2d57de667977","entry":"load_questions_from_dir","repo":"iDEA-iSAIL-Lab-UIUC/APEX","repo_kind":"official","path":"code/src/query.py","file_url":"https://github.com/iDEA-iSAIL-Lab-UIUC/APEX/blob/HEAD/code/src/query.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"51df2d57de667977"}},{"code_sha256_prefix":"5d40f691b98b3b24","entry":"positive_int","repo":"iDEA-iSAIL-Lab-UIUC/APEX","repo_kind":"official","path":"PKG_EXP/MetaQA/generate_query.py","file_url":"https://github.com/iDEA-iSAIL-Lab-UIUC/APEX/blob/HEAD/PKG_EXP/MetaQA/generate_query.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5d40f691b98b3b24"}},{"code_sha256_prefix":"c610c9ba3b321e3d","entry":"precision","repo":"iDEA-iSAIL-Lab-UIUC/APEX","repo_kind":"official","path":"code/src/metrics.py","file_url":"https://github.com/iDEA-iSAIL-Lab-UIUC/APEX/blob/HEAD/code/src/metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c610c9ba3b321e3d"}},{"code_sha256_prefix":"fa9e3f0df15d7987","entry":"predicate_counts","repo":"iDEA-iSAIL-Lab-UIUC/APEX","repo_kind":"official","path":"code/src/user.py","file_url":"https://github.com/iDEA-iSAIL-Lab-UIUC/APEX/blob/HEAD/code/src/user.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fa9e3f0df15d7987"}},{"code_sha256_prefix":"fdaa7d19b62a3565","entry":"query_vector","repo":"iDEA-iSAIL-Lab-UIUC/APEX","repo_kind":"official","path":"code/src/algorithms.py","file_url":"https://github.com/iDEA-iSAIL-Lab-UIUC/APEX/blob/HEAD/code/src/algorithms.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"fdaa7d19b62a3565"}},{"code_sha256_prefix":"b92170f581df785d","entry":"random_walk_with_restart","repo":"iDEA-iSAIL-Lab-UIUC/APEX","repo_kind":"official","path":"code/src/algorithms.py","file_url":"https://github.com/iDEA-iSAIL-Lab-UIUC/APEX/blob/HEAD/code/src/algorithms.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b92170f581df785d"}},{"code_sha256_prefix":"0e2103a8ddc3def1","entry":"recall","repo":"iDEA-iSAIL-Lab-UIUC/APEX","repo_kind":"official","path":"code/src/metrics.py","file_url":"https://github.com/iDEA-iSAIL-Lab-UIUC/APEX/blob/HEAD/code/src/metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0e2103a8ddc3def1"}},{"code_sha256_prefix":"009124768559899b","entry":"reuse","repo":"iDEA-iSAIL-Lab-UIUC/APEX","repo_kind":"official","path":"code/src/user.py","file_url":"https://github.com/iDEA-iSAIL-Lab-UIUC/APEX/blob/HEAD/code/src/user.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"009124768559899b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}