mlsanityData to 14 Oct 2026

APEX2: Adaptive and Extreme Summarization for Personalized Knowledge Graphs

arXiv 2412.17336 ↗First posted 23 Dec 2024cs.LG cs.AI cs.DBcited by 13

Not on the map. Why?

Abstract (arXiv)

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 APEX2, 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, APEX2 continuously tracks the interest shift and adjusts the previous summary. We evaluate APEX2 under an evolving query setting on benchmark KGs containing up to 12 million triples, summarizing with compression ratios ≤ 0.1%. The experiments show that APEX outperforms state-of-the-art baselines in terms of both query-answering accuracy and efficiency. Code is available at https://github.com/iDEA-iSAIL-Lab-UIUC/APEX.

Key facts. Cited by 13 papers in the map (data through 14 Oct 2026). Builds on 29 of its 80 references that are in the map. First posted on arXiv 23 Dec 2024.

Builds on

29 of 80 references.

References · 29

  1. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  2. 2016node2vec: Scalable Feature Learning for Networkscited by 1,918
  3. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,453
  4. 2022GraphCast: Learning skillful medium-range global weather forecastingcited by 267
  5. 2015A Review of Relational Machine Learning for Knowledge Graphscited by 265
  6. 2016Key-Value Memory Networks for Directly Reading Documentscited by 223
  7. 2017Variational Reasoning for Question Answering with Knowledge Graphcited by 170
  8. 2024Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAGcited by 123
  9. 2024Personalized Large Language Modelscited by 44
  10. 2024Heterogeneous Contrastive Learning for Foundation Models and Beyondcited by 27
  11. 2023Hierarchical Multi-Marginal Optimal Transport for Network Alignmentcited by 24
  12. 2020KompaRe: A Knowledge Graph Comparative Reasoning Systemcited by 20
17 more
  1. 2022MentorGNN: Deriving Curriculum for Pre-Training GNNscited by 18
  2. 2023Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspectivecited by 17
  3. 2016Graph Summarization Methods and Applications: A Surveycited by 16
  4. 2017An Analytical Study of Large SPARQL Query Logscited by 14
  5. 2024Can Graph Neural Networks Learn Language with Extremely Weak Text Supervision?cited by 13
  6. 2024Fair Anomaly Detection For Imbalanced Groupscited by 10
  7. 2020What is Normal, What is Strange, and What is Missing in a Knowledge Graph: Unified Characterization via Inductive Summarizationcited by 9
  8. 2020SSumM: Sparse Summarization of Massive Graphscited by 9
  9. 2024SpherE: Expressive and Interpretable Knowledge Graph Embedding for Set Retrievalcited by 8
  10. 2024Generating Fine-Grained Causality in Climate Time Series Data for Forecasting and Anomaly Detectioncited by 7
  11. 2018No Place to Hide: Catching Fraudulent Entities in Tensorscited by 6
  12. 2024Real-time Vehicle-to-Vehicle Communication Based Network Cooperative Control System through Distributed Database and Multimodal Perception: Demonstrated in Crossroadscited by 6
  13. 2020Incremental Lossless Graph Summarizationcited by 5
  14. 2020SOLAR: Sparse Orthogonal Learned and Random Embeddingscited by 4
  15. 2024Hypergraphs as Weighted Directed Self-Looped Graphs: Spectral Properties, Clustering, Cheeger Inequalitycited by 4
  16. 2024Local Clustering on Complex Graphs and Complex Hypergraphscited by 4
  17. 2024iSummary: Workload-based, Personalized Summaries for Knowledge Graphscited by 3

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 10; 2026: 2.

13 papers.

Sort:

By area:

  1. 2025Language in the Flow of Time: Time-Series-Paired Texts Weaved into a Unified Temporal Narrativecited by 40
  2. 2025Pave Your Own Path: Graph Gradual Domain Adaptation on Fused Gromov-Wasserstein Geodesicscited by 17
  3. 2025Graph4MM: Weaving Multimodal Learning with Structural Informationcited by 17
  4. 2024PyG-SSL: A Graph Self-Supervised Learning Toolkitcited by 14
  5. 2025Research on Large Language Model Cross-Cloud Privacy Protection and Collaborative Training based on Federated Learningcited by 11
  6. 2025Joint Optimal Transport and Embedding for Network Alignmentcited by 10
  7. 2025Hierarchical LoRA MoE for Efficient CTR Model Scalingcited by 10
  8. 2025NIRVANA: Structured Pruning Reimagined for Large Language Model Compressioncited by 6
  9. 2025Invariant Link Selector for Spatial-Temporal Out-of-Distribution Problemcited by 5
  10. 2025ClimateBench-M: A Multi-Modal Climate Data Benchmark with a Simple Generative Methodcited by 4
  11. 2025Learnable Spatial-Temporal Positional Encoding for Link Predictioncited by 3
  12. 2026OWLEYE: Zero-Shot Learner for Cross-Domain Graph Data Anomaly Detectioncited by 2
1 more
  1. 2026COREKG: Coreset-Guided Personalized Summarization of Knowledge Graphscited by 0