Type Information-Assisted Self-Supervised Knowledge Graph Denoising

• URL: http://arxiv.org/abs/2503.09916v1
• Date: Thu, 13 Mar 2025 00:12:27 GMT
• Title: Type Information-Assisted Self-Supervised Knowledge Graph Denoising
• Authors: Jiaqi Sun, Yujia Zheng, Xinshuai Dong, Haoyue Dai, Kun Zhang,
• Abstract summary: Existing approaches to noise detection rely on external facts, logical rule constraints, or structural embeddings.<n>We propose to exploit the consistency between entity and relation type information for noise detection.<n>We formalize type inconsistency noise as triples that deviate from the majority with respect to type-dependent reasoning.
• Score: 15.310157441397001
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Knowledge graphs serve as critical resources supporting intelligent systems, but they can be noisy due to imperfect automatic generation processes. Existing approaches to noise detection often rely on external facts, logical rule constraints, or structural embeddings. These methods are often challenged by imperfect entity alignment, flexible knowledge graph construction, and overfitting on structures. In this paper, we propose to exploit the consistency between entity and relation type information for noise detection, resulting a novel self-supervised knowledge graph denoising method that avoids those problems. We formalize type inconsistency noise as triples that deviate from the majority with respect to type-dependent reasoning along the topological structure. Specifically, we first extract a compact representation of a given knowledge graph via an encoder that models the type dependencies of triples. Then, the decoder reconstructs the original input knowledge graph based on the compact representation. It is worth noting that, our proposal has the potential to address the problems of knowledge graph compression and completion, although this is not our focus. For the specific task of noise detection, the discrepancy between the reconstruction results and the input knowledge graph provides an opportunity for denoising, which is facilitated by the type consistency embedded in our method. Experimental validation demonstrates the effectiveness of our approach in detecting potential noise in real-world data.

Related papers

• You Can't Ignore Either: Unifying Structure and Feature Denoising for Robust Graph Learning [34.52299775051481]
  We develop a unified graph denoising (UGD) framework to unravel the deadlock between structure and feature denoising. Specifically, a high-order neighborhood proximity evaluation method is proposed to recognize noisy edges. We also propose to refine noisy features with reconstruction based on a graph auto-encoder.
  arXiv  Detail & Related papers  (2024-08-01T16:43:55Z)
• Multi-modal Causal Structure Learning and Root Cause Analysis [67.67578590390907]
  We propose Mulan, a unified multi-modal causal structure learning method for root cause localization. We leverage a log-tailored language model to facilitate log representation learning, converting log sequences into time-series data. We also introduce a novel key performance indicator-aware attention mechanism for assessing modality reliability and co-learning a final causal graph.
  arXiv  Detail & Related papers  (2024-02-04T05:50:38Z)
• Improving the Robustness of Knowledge-Grounded Dialogue via Contrastive Learning [71.8876256714229]
  We propose an entity-based contrastive learning framework for improving the robustness of knowledge-grounded dialogue systems. Our method achieves new state-of-the-art performance in terms of automatic evaluation scores.
  arXiv  Detail & Related papers  (2024-01-09T05:16:52Z)
• Combating Bilateral Edge Noise for Robust Link Prediction [56.43882298843564]
  We propose an information-theory-guided principle, Robust Graph Information Bottleneck (RGIB), to extract reliable supervision signals and avoid representation collapse. Two instantiations, RGIB-SSL and RGIB-REP, are explored to leverage the merits of different methodologies. Experiments on six datasets and three GNNs with diverse noisy scenarios verify the effectiveness of our RGIB instantiations.
  arXiv  Detail & Related papers  (2023-11-02T12:47:49Z)
• Uncertainty-Aware Robust Learning on Noisy Graphs [22.848589361600382]
  We propose a novel uncertainty-aware graph learning framework inspired by distributionally robust optimization.<n>We use a graph neural network-based encoder to embed the node features and find the optimal node embeddings.<n>Such an uncertainty-aware learning process leads to improved node representations and a more robust graph predictive model.
  arXiv  Detail & Related papers  (2023-06-14T02:45:14Z)
• Deep Active Learning with Noise Stability [24.54974925491753]
  Uncertainty estimation for unlabeled data is crucial to active learning. We propose a novel algorithm that leverages noise stability to estimate data uncertainty. Our method is generally applicable in various tasks, including computer vision, natural language processing, and structural data analysis.
  arXiv  Detail & Related papers  (2022-05-26T13:21:01Z)
• Type-aware Embeddings for Multi-Hop Reasoning over Knowledge Graphs [18.56742938427262]
  Multi-hop reasoning over real-life knowledge graphs (KGs) is a highly challenging problem. To address this problem, it has been recently introduced a promising approach based on jointly embedding logical queries and KGs. We propose a novel TypE-aware Message Passing (TEMP) model, which enhances the entity and relation representations in queries.
  arXiv  Detail & Related papers  (2022-05-02T10:05:13Z)
• Context-Dependent Anomaly Detection with Knowledge Graph Embedding Models [0.0]
  We develop a framework for converting a context-dependent anomaly detection problem to a link prediction problem. We show that our method can detect context-dependent anomalies with a high degree of accuracy.
  arXiv  Detail & Related papers  (2022-03-17T14:36:12Z)
• Score matching enables causal discovery of nonlinear additive noise models [63.93669924730725]
  We show how to design a new generation of scalable causal discovery methods. We propose a new efficient method for approximating the score's Jacobian, enabling to recover the causal graph.
  arXiv  Detail & Related papers  (2022-03-08T21:34:46Z)
• Tackling Instance-Dependent Label Noise via a Universal Probabilistic Model [80.91927573604438]
  This paper proposes a simple yet universal probabilistic model, which explicitly relates noisy labels to their instances. Experiments on datasets with both synthetic and real-world label noise verify that the proposed method yields significant improvements on robustness.
  arXiv  Detail & Related papers  (2021-01-14T05:43:51Z)
• Guiding Graph Embeddings using Path-Ranking Methods for Error Detection innoisy Knowledge Graphs [0.0]
  This work presents various mainstream approaches and proposes a hybrid and modular methodology for the task. We compare different methods on two benchmarks and one real-world biomedical publications dataset, showcasing the potential of our approach.
  arXiv  Detail & Related papers  (2020-02-19T11:04:11Z)
• Learning Not to Learn in the Presence of Noisy Labels [104.7655376309784]
  We show that a new class of loss functions called the gambler's loss provides strong robustness to label noise across various levels of corruption. We show that training with this loss function encourages the model to "abstain" from learning on the data points with noisy labels.
  arXiv  Detail & Related papers  (2020-02-16T09:12:27Z)

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.