# APEX2: Adaptive and Extreme Summarization for Personalized Knowledge Graphs

arXiv: https://arxiv.org/abs/2412.17336 · HTML: https://mlsanity.com/paper/2412.17336/

## 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 (most cited first, 29 of 29)

- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [From Local to Global: A Graph RAG Approach to Query-Focused Summarization](https://mlsanity.com/paper/2404.16130/) (2024)
- [GraphCast: Learning skillful medium-range global weather forecasting](https://mlsanity.com/paper/2212.12794/) (2022)
- [A Review of Relational Machine Learning for Knowledge Graphs](https://mlsanity.com/paper/1503.00759/) (2015)
- [Key-Value Memory Networks for Directly Reading Documents](https://mlsanity.com/paper/1606.03126/) (2016)
- [Variational Reasoning for Question Answering with Knowledge Graph](https://mlsanity.com/paper/1709.04071/) (2017)
- [Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG](https://mlsanity.com/paper/2410.05983/) (2024)
- [Personalized Large Language Models](https://mlsanity.com/paper/2402.09269/) (2024)
- [Heterogeneous Contrastive Learning for Foundation Models and Beyond](https://mlsanity.com/paper/2404.00225/) (2024)
- [Hierarchical Multi-Marginal Optimal Transport for Network Alignment](https://mlsanity.com/paper/2310.04470/) (2023)
- [KompaRe: A Knowledge Graph Comparative Reasoning System](https://mlsanity.com/paper/2011.03189/) (2020)
- [MentorGNN: Deriving Curriculum for Pre-Training GNNs](https://mlsanity.com/paper/2208.09905/) (2022)
- [Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective](https://mlsanity.com/paper/2310.11451/) (2023)
- [Graph Summarization Methods and Applications: A Survey](https://mlsanity.com/paper/1612.04883/) (2016)
- [An Analytical Study of Large SPARQL Query Logs](https://mlsanity.com/paper/1708.00363/) (2017)
- [Can Graph Neural Networks Learn Language with Extremely Weak Text Supervision?](https://mlsanity.com/paper/2412.08174/) (2024)
- [Fair Anomaly Detection For Imbalanced Groups](https://mlsanity.com/paper/2409.10951/) (2024)
- [What is Normal, What is Strange, and What is Missing in a Knowledge Graph: Unified Characterization via Inductive Summarization](https://mlsanity.com/paper/2003.10412/) (2020)
- [SSumM: Sparse Summarization of Massive Graphs](https://mlsanity.com/paper/2006.01060/) (2020)
- [SpherE: Expressive and Interpretable Knowledge Graph Embedding for Set Retrieval](https://mlsanity.com/paper/2404.19130/) (2024)
- [Generating Fine-Grained Causality in Climate Time Series Data for Forecasting and Anomaly Detection](https://mlsanity.com/paper/2408.04254/) (2024)
- [No Place to Hide: Catching Fraudulent Entities in Tensors](https://mlsanity.com/paper/1810.06230/) (2018)
- [Real-time Vehicle-to-Vehicle Communication Based Network Cooperative Control System through Distributed Database and Multimodal Perception: Demonstrated in Crossroads](https://mlsanity.com/paper/2410.17576/) (2024)
- [Incremental Lossless Graph Summarization](https://mlsanity.com/paper/2006.09935/) (2020)
- [SOLAR: Sparse Orthogonal Learned and Random Embeddings](https://mlsanity.com/paper/2008.13225/) (2020)
- [Hypergraphs as Weighted Directed Self-Looped Graphs: Spectral Properties, Clustering, Cheeger Inequality](https://mlsanity.com/paper/2411.03331/) (2024)
- [Local Clustering on Complex Graphs and Complex Hypergraphs](https://mlsanity.com/paper/2412.03008/) (2024)
- [iSummary: Workload-based, Personalized Summaries for Knowledge Graphs](https://mlsanity.com/paper/2403.02934/) (2024)

## Built on by (most cited first, 13 of 13)

- [Language in the Flow of Time: Time-Series-Paired Texts Weaved into a Unified Temporal Narrative](https://mlsanity.com/paper/2502.08942/) (2025)
- [Pave Your Own Path: Graph Gradual Domain Adaptation on Fused Gromov-Wasserstein Geodesics](https://mlsanity.com/paper/2505.12709/) (2025)
- [Graph4MM: Weaving Multimodal Learning with Structural Information](https://mlsanity.com/paper/2510.16990/) (2025)
- [PyG-SSL: A Graph Self-Supervised Learning Toolkit](https://mlsanity.com/paper/2412.21151/) (2024)
- [Research on Large Language Model Cross-Cloud Privacy Protection and Collaborative Training based on Federated Learning](https://mlsanity.com/paper/2503.12226/) (2025)
- [Joint Optimal Transport and Embedding for Network Alignment](https://mlsanity.com/paper/2502.19334/) (2025)
- [Hierarchical LoRA MoE for Efficient CTR Model Scaling](https://mlsanity.com/paper/2510.10432/) (2025)
- [NIRVANA: Structured Pruning Reimagined for Large Language Model Compression](https://mlsanity.com/paper/2509.14230/) (2025)
- [Invariant Link Selector for Spatial-Temporal Out-of-Distribution Problem](https://mlsanity.com/paper/2505.24178/) (2025)
- [ClimateBench-M: A Multi-Modal Climate Data Benchmark with a Simple Generative Method](https://mlsanity.com/paper/2504.07394/) (2025)
- [Learnable Spatial-Temporal Positional Encoding for Link Prediction](https://mlsanity.com/paper/2506.08309/) (2025)
- [OWLEYE: Zero-Shot Learner for Cross-Domain Graph Data Anomaly Detection](https://mlsanity.com/paper/2601.19102/) (2026)
- [COREKG: Coreset-Guided Personalized Summarization of Knowledge Graphs](https://mlsanity.com/paper/2605.14900/) (2026)

## 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.