Noisy Positive-Unlabeled Learning with Self-Training for Speculative Knowledge Graph Reasoning

• URL: http://arxiv.org/abs/2306.07512v1
• Date: Tue, 13 Jun 2023 02:43:21 GMT
• Title: Noisy Positive-Unlabeled Learning with Self-Training for Speculative Knowledge Graph Reasoning
• Authors: Ruijie Wang, Baoyu Li, Yichen Lu, Dachun Sun, Jinning Li, Yuchen Yan, Shengzhong Liu, Hanghang Tong, Tarek F. Abdelzaher
• Abstract summary: This paper studies speculative reasoning task on real-world knowledge graphs (KG) that contain both textitfalse negative issue (i.e., potential true facts being excluded) and textitfalse positive issue (i.e., unreliable or outdated facts being included) We propose a variational framework, namely nPUGraph, that jointly estimates the correctness of both collected and uncollected facts.
• Score: 31.62771133978441
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper studies speculative reasoning task on real-world knowledge graphs (KG) that contain both \textit{false negative issue} (i.e., potential true facts being excluded) and \textit{false positive issue} (i.e., unreliable or outdated facts being included). State-of-the-art methods fall short in the speculative reasoning ability, as they assume the correctness of a fact is solely determined by its presence in KG, making them vulnerable to false negative/positive issues. The new reasoning task is formulated as a noisy Positive-Unlabeled learning problem. We propose a variational framework, namely nPUGraph, that jointly estimates the correctness of both collected and uncollected facts (which we call \textit{label posterior}) and updates model parameters during training. The label posterior estimation facilitates speculative reasoning from two perspectives. First, it improves the robustness of a label posterior-aware graph encoder against false positive links. Second, it identifies missing facts to provide high-quality grounds of reasoning. They are unified in a simple yet effective self-training procedure. Empirically, extensive experiments on three benchmark KG and one Twitter dataset with various degrees of false negative/positive cases demonstrate the effectiveness of nPUGraph.

Related papers

• LLM Critics Help Catch Bugs in Mathematics: Towards a Better Mathematical Verifier with Natural Language Feedback [71.95402654982095]
  We propose Math-Minos, a natural language feedback-enhanced verifier. Our experiments reveal that a small set of natural language feedback can significantly boost the performance of the verifier.
  arXiv  Detail & Related papers  (2024-06-20T06:42:27Z)
• NP$^2$L: Negative Pseudo Partial Labels Extraction for Graph Neural Networks [48.39834063008816]
  Pseudo labels are used in graph neural networks (GNNs) to assist learning at the message-passing level. In this paper, we introduce a new method to use pseudo labels in GNNs. We show that our method is more accurate if they are selected by not overlapping partial labels and defined as negative node pairs relations.
  arXiv  Detail & Related papers  (2023-10-02T11:13:59Z)
• ReCEval: Evaluating Reasoning Chains via Correctness and Informativeness [67.49087159888298]
  ReCEval is a framework that evaluates reasoning chains via two key properties: correctness and informativeness. We show that ReCEval effectively identifies various error types and yields notable improvements compared to prior methods.
  arXiv  Detail & Related papers  (2023-04-21T02:19:06Z)
• When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method [40.25499257944916]
  Real-world datasets are both noisily labeled and class-imbalanced. We propose a representation calibration method RCAL. We derive theoretical results to discuss the effectiveness of our representation calibration.
  arXiv  Detail & Related papers  (2022-11-20T11:36:48Z)
• Adversarial Contrastive Learning for Evidence-aware Fake News Detection with Graph Neural Networks [20.282527436527765]
  We propose a unified Graph-based sEmantic structure mining framework with ConTRAstive Learning, namely GETRAL in short. We first model claims and evidences as graph-structured data to capture the long-distance semantic dependency. Then the fine-grained semantic representations are fed into the claim-evidence interaction module for predictions.
  arXiv  Detail & Related papers  (2022-10-11T14:54:37Z)
• Don't Explain Noise: Robust Counterfactuals for Randomized Ensembles [50.81061839052459]
  We formalize the generation of robust counterfactual explanations as a probabilistic problem. We show the link between the robustness of ensemble models and the robustness of base learners. Our method achieves high robustness with only a small increase in the distance from counterfactual explanations to their initial observations.
  arXiv  Detail & Related papers  (2022-05-27T17:28:54Z)
• Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion [41.34363699523586]
  We propose positive-unlabeled learning with adversarial data augmentation (PUDA) for knowledge graph completion. PUDA tailors positive-unlabeled risk estimator for the KGC task to deal with the false negative issue. To address the data sparsity issue, PUDA achieves a data augmentation strategy by unifying adversarial training and positive-unlabeled learning.
  arXiv  Detail & Related papers  (2022-05-02T13:33:27Z)
• L2B: Learning to Bootstrap Robust Models for Combating Label Noise [52.02335367411447]
  This paper introduces a simple and effective method, named Learning to Bootstrap (L2B) It enables models to bootstrap themselves using their own predictions without being adversely affected by erroneous pseudo-labels. It achieves this by dynamically adjusting the importance weight between real observed and generated labels, as well as between different samples through meta-learning.
  arXiv  Detail & Related papers  (2022-02-09T05:57:08Z)
• Deconfounded Training for Graph Neural Networks [98.06386851685645]
  We present a new paradigm of decon training (DTP) that better mitigates the confounding effect and latches on the critical information. Specifically, we adopt the attention modules to disentangle the critical subgraph and trivial subgraph. It allows GNNs to capture a more reliable subgraph whose relation with the label is robust across different distributions.
  arXiv  Detail & Related papers  (2021-12-30T15:22:35Z)
• Boosting Contrastive Self-Supervised Learning with False Negative Cancellation [40.71224235172881]
  A fundamental problem in contrastive learning is mitigating the effects of false negatives. We propose novel approaches to identify false negatives, as well as two strategies to mitigate their effect. Our method exhibits consistent improvements over existing contrastive learning-based methods.
  arXiv  Detail & Related papers  (2020-11-23T22:17:21Z)

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.