CLARK: Closed-loop Learning for Adaptive Reasoning over Knowledge Graphs

• URL: http://arxiv.org/abs/2607.19996v1
• Date: Wed, 22 Jul 2026 10:30:45 GMT
• Title: CLARK: Closed-loop Learning for Adaptive Reasoning over Knowledge Graphs
• Abstract summary: CLARK (Closed-loop Learning for Adaptive Reasoning over Knowledge Graphs) is a framework that integrates knowledge graphs, symbolic rule mining, and probabilistic reasoning.<n>We evaluate CLARK on two medical datasets, analysing both rule quality and downstream classification performance.
• Score: 2.2889981393105554
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Machine Learning models are widely used for automating classification tasks by extracting statistical patterns from data. However, their performance deteriorates if the data distribution changes, making them ill-suited to handle uncertain and evolving information. Moreover, they provide limited support for integrating prior knowledge. To address these limitations, we present CLARK (Closed-loop Learning for Adaptive Reasoning over Knowledge Graphs), a framework that integrates knowledge graphs, symbolic rule mining, and probabilistic reasoning under the Logic Programs with Markov Logic Networks (LP$^{\text{MLN}}$) formalism. Starting from CACTUS-derived KGs, CLARK translates graph structure into an LP$^{\text{MLN}}$ program and iteratively enriches it with candidate rules proposed by symbolic learners. These rules are calibrated through probabilistic weight learning, enabling reasoning under uncertainty and refinement of the underlying graph structure. We evaluate CLARK on two medical datasets, analysing both rule quality and downstream classification performance. Results demonstrate that CLARK leads to improved classification performance and more generalisable inference. Overall, CLARK provides a principled approach to constructing adaptive, interpretable, knowledge-driven models for classification.

Related papers

• VulReaD: Knowledge-Graph-guided Software Vulnerability Reasoning and Detection [37.944533057524986]
  VulReaD is a knowledge-graph-guided approach for vulnerability reasoning and detection.<n>It generates CWE-consistent contrastive reasoning supervision, enabling student model training without manual annotations.<n>It improves binary F1 by 8-10% and multi-class classification by 30% Macro-F1 and 18% Micro-F1.
  arXiv  Detail & Related papers  (2026-02-11T12:24:51Z)
• Learning from Sufficient Rationales: Analysing the Relationship Between Explanation Faithfulness and Token-level Regularisation Strategies [5.225254533678075]
  We investigate the effects of rationale information on model performance.<n>We find that highly informative rationales are not likely to help classify the instance correctly.<n>We also find that incorporating rationale information in model inputs can boost cross-domain classification, but results are inconsistent per task and model type.
  arXiv  Detail & Related papers  (2025-11-20T13:39:20Z)
• G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledge [88.82814893945077]
  Large language models (LLMs) excel at complex reasoning but remain limited by static and incomplete parametric knowledge.<n>Recent graph-enhanced RAG (GraphRAG) attempts to bridge this gap by constructing tailored graphs and enabling LLMs to reason on them.<n>G-reasoner is a unified framework that integrates graph and language foundation models for reasoning over diverse graph-structured knowledge.
  arXiv  Detail & Related papers  (2025-09-29T04:38:12Z)
• Two Birds with One Stone: Enhancing Uncertainty Quantification and Interpretability with Graph Functional Neural Process [27.760002432327962]
  Graph neural networks (GNNs) are powerful tools on graph data.<n>However, their predictions are mis-calibrated and lack interpretability.<n>We propose a new uncertainty-aware and interpretable graph classification model.
  arXiv  Detail & Related papers  (2025-08-23T17:48:05Z)
• 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)
• Knowledge Graph Enhanced Generative Multi-modal Models for Class-Incremental Learning [51.0864247376786]
  We introduce a Knowledge Graph Enhanced Generative Multi-modal model (KG-GMM) that builds an evolving knowledge graph throughout the learning process.<n>During testing, we propose a Knowledge Graph Augmented Inference method that locates specific categories by analyzing relationships within the generated text.
  arXiv  Detail & Related papers  (2025-03-24T07:20:43Z)
• Markov Process-Based Graph Convolutional Networks for Entity Classification in Knowledge Graphs [1.6252896527001486]
  We introduce a Markov process-based architecture into well-known Graph Convolutional Networks (GCNs)<n>This end-to-end network learns the prediction of class affiliation of entities in Knowledge Graphs within a Markov process.<n>Experiments show a performance improvement over existing models in several studied architectures and datasets.
  arXiv  Detail & Related papers  (2024-12-23T09:59:49Z)
• Deep Contrastive Graph Learning with Clustering-Oriented Guidance [61.103996105756394]
  Graph Convolutional Network (GCN) has exhibited remarkable potential in improving graph-based clustering. Models estimate an initial graph beforehand to apply GCN. Deep Contrastive Graph Learning (DCGL) model is proposed for general data clustering.
  arXiv  Detail & Related papers  (2024-02-25T07:03:37Z)
• XAL: EXplainable Active Learning Makes Classifiers Better Low-resource Learners [71.8257151788923]
  We propose a novel Explainable Active Learning framework (XAL) for low-resource text classification.<n>XAL encourages classifiers to justify their inferences and delve into unlabeled data for which they cannot provide reasonable explanations.<n>Experiments on six datasets show that XAL achieves consistent improvement over 9 strong baselines.
  arXiv  Detail & Related papers  (2023-10-09T08:07:04Z)
• Towards Unsupervised Deep Graph Structure Learning [67.58720734177325]
  We propose an unsupervised graph structure learning paradigm, where the learned graph topology is optimized by data itself without any external guidance. Specifically, we generate a learning target from the original data as an "anchor graph", and use a contrastive loss to maximize the agreement between the anchor graph and the learned graph.
  arXiv  Detail & Related papers  (2022-01-17T11:57:29Z)
• EvoLearner: Learning Description Logics with Evolutionary Algorithms [2.0096667731426976]
  Classifying nodes in knowledge graphs is an important task, e.g., predicting missing types of entities, predicting which molecules cause cancer, or predicting which drugs are promising treatment candidates. We propose EvoLearner - an evolutionary approach to learn description logic concepts from positive and negative examples.
  arXiv  Detail & Related papers  (2021-11-08T23:47:39Z)
• Few-Shot Incremental Learning with Continually Evolved Classifiers [46.278573301326276]
  Few-shot class-incremental learning (FSCIL) aims to design machine learning algorithms that can continually learn new concepts from a few data points. The difficulty lies in that limited data from new classes not only lead to significant overfitting issues but also exacerbate the notorious catastrophic forgetting problems. We propose a Continually Evolved CIF ( CEC) that employs a graph model to propagate context information between classifiers for adaptation.
  arXiv  Detail & Related papers  (2021-04-07T10:54:51Z)

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.