Import What You Need: Learning When and How to Augment EHR Graphs with External Knowledge

• URL: http://arxiv.org/abs/2609.01839v1
• Date: Tue, 01 Sep 2026 20:16:55 GMT
• Title: Import What You Need: Learning When and How to Augment EHR Graphs with External Knowledge
• Abstract summary: We propose a Reinforcement learning-based dynamic Topology Augmentation framework that casts KG import as a per-visit, budget-aware policy.<n>ReTA consistently outperforms strong baselines while remaining efficient, transfers across datasets and knowledge graphs, and yields interpretable augmentation patterns.
• Score: 21.61245033916194
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Longitudinal prediction from electronic health records (EHRs) is limited by the sparsity and irregularity in patient trajectories, and knowledge augmentation with external knowledge graphs (KGs) offers a promising way to alleviate these issues. However, most existing methods perform fixed, context-agnostic topology augmentation by adding the same KG nodes and edges regardless of a patient's evolving state. We propose ReTA, a Reinforcement learning-based dynamic Topology Augmentation framework that casts KG import as a per-visit, budget-aware policy. ReTA first constructs an offline refined pool of KG-grounded templates, then learns a policy to select one augment action per visit from three options: Soft Import, which enriches node features without modifying graph topology, Hard Import, which grafts a compact KG subgraph onto the visit graph to create message-passing shortcuts, and Skip, which leaves the visit unaugmented when the base encoder is already confident. To stabilize learning, ReTA employs a decoupled encoder that processes semantic and structural signals in separate channels and fuses them via adaptive gating. Experiments on MIMIC-III and MIMIC-IV across diagnosis prediction, mortality, and readmission show that ReTA consistently outperforms strong baselines while remaining efficient, transfers across datasets and knowledge graphs, and yields interpretable augmentation patterns. The robust gains under sparse supervision highlight the advantage of ReTA's dynamic decision to import knowledge, boosting accuracy while curbing costs.

Related papers

• Graph-Anchored Knowledge Indexing for Retrieval-Augmented Generation [53.42323544075114]
  We propose GraphAnchor, a novel Graph-Anchored Knowledge Indexing approach.<n> Experiments on four multi-hop question answering benchmarks demonstrate the effectiveness of GraphAnchor.
  arXiv  Detail & Related papers  (2026-01-23T05:41:05Z)
• Rate-Distortion Guided Knowledge Graph Construction from Lecture Notes Using Gromov-Wasserstein Optimal Transport [0.06524460254566902]
  Task-oriented knowledge graphs (KGs) enable AI-powered learning assistant systems to automatically generate high-quality multiple-choice questions (MCQs)<n>Yet converting unstructured educational materials, such as lecture notes and slides, into KGs that capture key pedagogical content remains difficult.<n>We propose a framework for knowledge graph construction and refinement grounded in rate-distortion (RD) theory and optimal transport geometry.
  arXiv  Detail & Related papers  (2025-11-18T15:37:39Z)
• Enrich-on-Graph: Query-Graph Alignment for Complex Reasoning with LLM Enriching [61.824094419641575]
  Large Language Models (LLMs) struggle with hallucinations and factual errors in knowledge-intensive scenarios like knowledge graph question answering (KGQA)<n>We attribute this to the semantic gap between structured knowledge graphs (KGs) and unstructured queries, caused by inherent differences in their focuses and structures.<n>Existing methods usually employ resource-intensive, non-scalable reasoning on vanilla KGs, but overlook this gap.<n>We propose a flexible framework, Enrich-on-Graph (EoG), which leverages LLMs' prior knowledge to enrich KGs, bridge the semantic gap between graphs and queries.
  arXiv  Detail & Related papers  (2025-09-25T06:48:52Z)
• Explainable Knowledge Graph Retrieval-Augmented Generation (KG-RAG) with KG-SMILE [0.03908906925636173]
  We develop a method-agnostic, perturbation-based framework that provides token and component-level interoperability for Graph RAG using SMILE.<n> KG-SMILE identifies the graph entities and relations most influential to generated outputs, thereby making RAG more transparent.<n>Our findings show that KG-SMILE produces stable, human-aligned explanations, demonstrating its capacity to balance model effectiveness with interpretability.
  arXiv  Detail & Related papers  (2025-09-03T18:29:30Z)
• Toward accurate RUL and SOH estimation using reinforced graph-based PINNs enhanced with dynamic weights [0.0]
  We propose a framework that combines physics-based supervision with advanced-temporal learning.<n>Q-learning agents dynamically assign weights to physics-informed loss terms, improving generalization across real-time industrial systems.<n>In both RUL and SOH estimation tasks, the proposed method consistently outperforms state-of-the-art models.
  arXiv  Detail & Related papers  (2025-07-13T19:49:12Z)
• Knowledge Fusion via Bidirectional Information Aggregation [20.309309990375134]
  Knowledge graphs (KGs) are the cornerstone of the semantic web, offering up-to-date representations of real-world entities and relations.<n>Large language models (LLMs) remain largely static after pre-training, causing their internal knowledge to become outdated and limiting their utility in time-sensitive web applications.<n>We introduce KGA, a novel framework that dynamically integrates external KGs into LLMs exclusively at inference-time without any parameter modification.
  arXiv  Detail & Related papers  (2025-07-11T15:57:37Z)
• Learning Efficient and Generalizable Graph Retriever for Knowledge-Graph Question Answering [75.12322966980003]
  Large Language Models (LLMs) have shown strong inductive reasoning ability across various domains.<n>Most existing RAG pipelines rely on unstructured text, limiting interpretability and structured reasoning.<n>Recent studies have explored integrating knowledge graphs with LLMs for knowledge graph question answering.<n>We propose RAPL, a novel framework for efficient and effective graph retrieval in KGQA.
  arXiv  Detail & Related papers  (2025-06-11T12:03:52Z)
• Normalizing Flow-based Neural Process for Few-Shot Knowledge Graph Completion [69.55700751102376]
  Few-shot knowledge graph completion (FKGC) aims to predict missing facts for unseen relations with few-shot associated facts. Existing FKGC methods are based on metric learning or meta-learning, which often suffer from the out-of-distribution and overfitting problems. In this paper, we propose a normalizing flow-based neural process for few-shot knowledge graph completion (NP-FKGC)
  arXiv  Detail & Related papers  (2023-04-17T11:42:28Z)
• Dynamic Graph Enhanced Contrastive Learning for Chest X-ray Report Generation [92.73584302508907]
  We propose a knowledge graph with Dynamic structure and nodes to facilitate medical report generation with Contrastive Learning. In detail, the fundamental structure of our graph is pre-constructed from general knowledge. Each image feature is integrated with its very own updated graph before being fed into the decoder module for report generation.
  arXiv  Detail & Related papers  (2023-03-18T03:53:43Z)
• Explainable Sparse Knowledge Graph Completion via High-order Graph Reasoning Network [111.67744771462873]
  This paper proposes a novel explainable model for sparse Knowledge Graphs (KGs) It combines high-order reasoning into a graph convolutional network, namely HoGRN. It can not only improve the generalization ability to mitigate the information insufficiency issue but also provide interpretability.
  arXiv  Detail & Related papers  (2022-07-14T10:16:56Z)
• Simple and Effective Relation-based Embedding Propagation for Knowledge Representation Learning [15.881121633396832]
  We propose the Relation-based Embedding Propagation (REP) method to adapt pretrained graph embeddings with context. We show that REP brings about 10% relative improvement to triplet-based embedding methods on OGBL-WikiKG2. It takes 5%-83% time to achieve comparable results as the state-of-the-art GC-OTE.
  arXiv  Detail & Related papers  (2022-05-13T06:02:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.