# Towards Pattern-aware Data Augmentation for Temporal Knowledge Graph Completion

arXiv: https://arxiv.org/abs/2501.00252 · HTML: https://mlsanity.com/paper/2501.00252/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 65 references that are in the map.
- First posted on arXiv 31 Dec 2024.

## Builds on (most cited first, 24 of 24)

- [Self-Supervised Learning of Graph Neural Networks: A Unified Review](https://mlsanity.com/paper/2102.10757/) (2021)
- [G-Mixup: Graph Data Augmentation for Graph Classification](https://mlsanity.com/paper/2202.07179/) (2022)
- [Learning Sequence Encoders for Temporal Knowledge Graph Completion](https://mlsanity.com/paper/1809.03202/) (2018)
- [Data Augmentation for Deep Graph Learning: A Survey](https://mlsanity.com/paper/2202.08235/) (2022)
- [Tensor Decompositions for temporal knowledge base completion](https://mlsanity.com/paper/2004.04926/) (2020)
- [An Empirical Study of Graph Contrastive Learning](https://mlsanity.com/paper/2109.01116/) (2021)
- [Temporal Knowledge Graph Reasoning Based on Evolutional Representation Learning](https://mlsanity.com/paper/2104.10353/) (2021)
- [Diachronic Embedding for Temporal Knowledge Graph Completion](https://mlsanity.com/paper/1907.03143/) (2019)
- [TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion](https://mlsanity.com/paper/2010.03526/) (2020)
- [Temporal Knowledge Graph Reasoning with Historical Contrastive Learning](https://mlsanity.com/paper/2211.10904/) (2022)
- [Confidence May Cheat: Self-Training on Graph Neural Networks under Distribution Shift](https://mlsanity.com/paper/2201.11349/) (2022)
- [Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shift](https://mlsanity.com/paper/2211.02843/) (2022)
- [GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation](https://mlsanity.com/paper/2310.00800/) (2023)
- [Temporal Knowledge Base Completion: New Algorithms and Evaluation Protocols](https://mlsanity.com/paper/2005.05035/) (2020)
- [TILP: Differentiable Learning of Temporal Logical Rules on Knowledge Graphs](https://mlsanity.com/paper/2402.12309/) (2024)
- [Toward Degree Bias in Embedding-Based Knowledge Graph Completion](https://mlsanity.com/paper/2302.05044/) (2023)
- [Localised Adaptive Spatial-Temporal Graph Neural Network](https://mlsanity.com/paper/2306.06930/) (2023)
- [Positive-Unlabeled Learning with Adversarial Data Augmentation for Knowledge Graph Completion](https://mlsanity.com/paper/2205.00904/) (2022)
- [Knowledge Graph Completion with Counterfactual Augmentation](https://mlsanity.com/paper/2302.13083/) (2023)
- [Comprehensive Analysis of Negative Sampling in Knowledge Graph Representation Learning](https://mlsanity.com/paper/2206.10140/) (2022)
- [Time-aware Path Reasoning on Knowledge Graph for Recommendation](https://mlsanity.com/paper/2108.02634/) (2021)
- [Negative Sampling in Knowledge Graph Representation Learning: A Review](https://mlsanity.com/paper/2402.19195/) (2024)
- [Spatio-Temporal Contrastive Learning Enhanced GNNs for Session-based Recommendation](https://mlsanity.com/paper/2209.11461/) (2022)
- [RevGNN: Negative Sampling Enhanced Contrastive Graph Learning for Academic Reviewer Recommendation](https://mlsanity.com/paper/2407.20684/) (2024)

## Abstract (arXiv)

Predicting missing facts for temporal knowledge graphs (TKGs) is a fundamental task, called temporal knowledge graph completion (TKGC). One key challenge in this task is the imbalance in data distribution, where facts are unevenly spread across entities and timestamps. This imbalance can lead to poor completion performance or long-tail entities and timestamps, and unstable training due to the introduction of false negative samples. Unfortunately, few previous studies have investigated how to mitigate these effects. Moreover, for the first time, we found that existing methods suffer from model preferences, revealing that entities with specific properties (e.g., recently active) are favored by different models. Such preferences will lead to error accumulation and further exacerbate the effects of imbalanced data distribution, but are overlooked by previous studies. To alleviate the impacts of imbalanced data and model preferences, we introduce Booster, the first data augmentation strategy for TKGs. The unique requirements here lie in generating new samples that fit the complex semantic and temporal patterns within TKGs, and identifying hard-learning samples specific to models. Therefore, we propose a hierarchical scoring algorithm based on triadic closures within TKGs. By incorporating both global semantic patterns and local time-aware structures, the algorithm enables pattern-aware validation for new samples. Meanwhile, we propose a two-stage training approach to identify samples that deviate from the model's preferred patterns. With a well-designed frequency-based filtering strategy, this approach also helps to avoid the misleading of false negatives. Experiments justify that Booster can seamlessly adapt to existing TKGC models and achieve up to an 8.7% performance improvement.