Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

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

About

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negative issue} (i.e., potential true facts being excluded) and \textit{false positive issue} (i.e., unreliable or outdated facts being included).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.

Ruijie Wang, Baoyu Li, Yichen Lu, Dachun Sun, Jinning Li, Yuchen Yan, Shengzhong Liu, Hanghang Tong, Tarek F. Abdelzaher• 2023

Related benchmarks

TaskDatasetResultRank
Knowledge Graph ReasoningFB15k-237 (test)
HITS@3 (Avg)0.343
29
Link PredictionTwitter ptb_rate = 0.3 (noisy and incomplete)
MRR3
13
Knowledge Graph ReasoningFB15K ptb_rate=0.7 (test)
MRR36.5
12
Knowledge Graph ReasoningFB15K-237 ptb_rate=0.7 (test)
MRR0.243
12
Knowledge Graph ReasoningWN18 ptb_rate=0.7 (test)
MRR0.247
12
Knowledge Graph ReasoningWN18
MRR0.493
12
Knowledge Graph ReasoningFB15K ptb_rate = 0.5 (test)
MRR0.417
12
Knowledge Graph ReasoningFB15K-237 ptb_rate = 0.5 (test)
MRR0.258
12
Knowledge Graph ReasoningWN18 ptb_rate = 0.5 (test)
MRR0.373
12
Knowledge Graph ReasoningWN18 (test)
MRR0.63
12
Showing 10 of 10 rows

Other info

Follow for update