On the Power of Heuristics in Temporal Graphs
Preprint
Abstract
Dynamic graph datasets often exhibit strong temporal patterns, such as recency, which prioritizes recent interactions, and popularity, which favors frequently occurring nodes. We demonstrate that simple heuristics leveraging only these patterns can perform on par or outperform state-of-the-art neural network models under standard evaluation protocols. To further explore these dynamics, we introduce metrics that quantify the impact of recency and popularity across datasets. Our experiments on BenchTemp and the Temporal Graph Benchmark show that our approaches achieve state-of-the-art performance across all datasets in the latter and secure top ranks on multiple datasets in the former. These results emphasize the importance of refined evaluation schemes to enable fair comparisons and promote the development of more robust temporal graph models. Additionally, they reveal that current deep learning methods often struggle to capture the key patterns underlying predictions in real-world temporal graphs. For reproducibility, we have made our code publicly available.Keywords
All Related Versions
This publication has 9 references indexed in Scilit:
- A survey on popularity bias in recommender systemsUser Modeling and User-Adapted Interaction, 2024
- Bias and Debias in Recommender System: A Survey and Future DirectionsACM Transactions on Information Systems, 2023
- A Survey on the Fairness of Recommender SystemsACM Transactions on Information Systems, 2023
- Temporal Graph Benchmark for Machine Learning on Temporal Graphs2023
- Towards Better Dynamic Graph Learning: New Architecture and Unified Library2023
- Towards Better Evaluation for Dynamic Link Prediction2022
- Neural Temporal Walks: Motif-Aware Representation Learning on Continuous-Time Dynamic Graphs2022
- Bringing Light Into the Dark: A Large-Scale Evaluation of Knowledge Graph Embedding Models Under a Unified FrameworkIEEE Transactions on Pattern Analysis and Machine Intelligence, 2021
- Predicting Dynamic Embedding Trajectory in Temporal Interaction Networks2019