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

arXiv: https://arxiv.org/abs/2306.07512 · HTML: https://mlsanity.com/paper/2306.07512/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 28 of its 48 references that are in the map.
- First posted on arXiv 13 Jun 2023.

## Builds on (most cited first, 28 of 28)

- [Modeling Relational Data with Graph Convolutional Networks](https://mlsanity.com/paper/1703.06103/) (2017)
- [Embedding Entities and Relations for Learning and Inference in Knowledge Bases](https://mlsanity.com/paper/1412.6575/) (2014)
- [RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space](https://mlsanity.com/paper/1902.10197/) (2019)
- [Convolutional 2D Knowledge Graph Embeddings](https://mlsanity.com/paper/1707.01476/) (2017)
- [Composition-based Multi-Relational Graph Convolutional Networks](https://mlsanity.com/paper/1911.03082/) (2019)
- [Learning from positive and unlabeled data: a survey](https://mlsanity.com/paper/1811.04820/) (2018)
- [Learning Sequence Encoders for Temporal Knowledge Graph Completion](https://mlsanity.com/paper/1809.03202/) (2018)
- [A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network](https://mlsanity.com/paper/1712.02121/) (2017)
- [RippleNet: Propagating User Preferences on the Knowledge Graph for Recommender Systems](https://mlsanity.com/paper/1803.03467/) (2018)
- [Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning](https://mlsanity.com/paper/2104.10353/) (2021)
- [Question Answering Over Temporal Knowledge Graphs](https://mlsanity.com/paper/2106.01515/) (2021)
- [Knowledge Graph Completion via Complex Tensor Factorization](https://mlsanity.com/paper/1702.06879/) (2017)
- [KBGAN: Adversarial Learning for Knowledge Graph Embeddings](https://mlsanity.com/paper/1711.04071/) (2017)
- [NSCaching: Simple and Efficient Negative Sampling for Knowledge Graph Embedding](https://mlsanity.com/paper/1812.06410/) (2018)
- [AceKG: A Large-scale Knowledge Graph for Academic Data Mining](https://mlsanity.com/paper/1807.08484/) (2018)
- [Structure Aware Negative Sampling in Knowledge Graphs](https://mlsanity.com/paper/2009.11355/) (2020)
- [Estimating the class prior and posterior from noisy positives and unlabeled data](https://mlsanity.com/paper/1606.08561/) (2016)
- [Embedding Uncertain Knowledge Graphs](https://mlsanity.com/paper/1811.10667/) (2018)
- [Probabilistic Box Embeddings for Uncertain Knowledge Graph Reasoning](https://mlsanity.com/paper/2104.04597/) (2021)
- [Learning to Sample and Aggregate: Few-shot Reasoning over Temporal Knowledge Graphs](https://mlsanity.com/paper/2210.08654/) (2022)
- [Instance-Dependent PU Learning by Bayesian Optimal Relabeling](https://mlsanity.com/paper/1808.02180/) (2018)
- [DyDiff-VAE: A Dynamic Variational Framework for Information Diffusion Prediction](https://mlsanity.com/paper/2106.03251/) (2021)
- [Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion](https://mlsanity.com/paper/2205.00904/) (2022)
- [Unsupervised Belief Representation Learning with Information-Theoretic Variational Graph Auto-Encoders](https://mlsanity.com/paper/2110.00210/) (2021)
- [RETE: Retrieval-Enhanced Temporal Event Forecasting on Unified Query Product Evolutionary Graph](https://mlsanity.com/paper/2202.06129/) (2022)
- [Author Name Disambiguation on Heterogeneous Information Network with Adversarial Representation Learning](https://mlsanity.com/paper/2002.09803/) (2020)
- [Hierarchical Overlapping Belief Estimation by Structured Matrix Factorization](https://mlsanity.com/paper/2002.05797/) (2020)
- [Mutually-paced Knowledge Distillation for Cross-lingual Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2303.14898/) (2023)

## Built on by (most cited first, 2 of 2)

- [Subspace Alignment for Vision-Language Model Test-time Adaptation](https://mlsanity.com/paper/2601.08139/) (2026)
- [Mixture of Sequence: Theme-Aware Mixture-of-Experts for Long-Sequence Recommendation](https://mlsanity.com/paper/2604.20858/) (2026)

## Abstract (arXiv)

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). 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 textitlabel 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.