Noisy Positive-Unlabeled Learning with Self-Training for Speculative Knowledge Graph Reasoning
This addresses the challenge of unreliable reasoning in real-world knowledge graphs for applications like data mining and AI systems, representing an incremental improvement over existing methods.
The paper tackles the problem of speculative reasoning on knowledge graphs with false negative and false positive facts by formulating it as a noisy Positive-Unlabeled learning problem and proposing nPUGraph, a variational framework that jointly estimates fact correctness and updates model parameters, achieving effectiveness demonstrated through experiments on three benchmark KG datasets and one Twitter dataset.
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negative issue} (i.e., potential true facts being excluded) and \textit{false positive issue} (i.e., unreliable or outdated facts being included).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.