Aiyappa et al., "Implicit degree bias in the link prediction task" (2025)

Rachith Aiyappa, Xin Wang, Munjung Kim, Ozgur Can Seckin, Jisung Yoon, Yong-Yeol Ahn, and Sadamori Kojaku, ICML (2025)
ICML | arXiv | Code | Data

@inproceedings{aiyappa2025implicit,
    author = {Rachith Aiyappa and Xin Wang and Munjung Kim and Ozgur Can Seckin and Jisung Yoon and Yong-Yeol Ahn and Sadamori Kojaku},
    title = {Implicit degree bias in the link prediction task},
    booktitle = {Proceedings of the 42nd International Conference on Machine Learning (ICML)},
    volume = {267},
    pages = {874--908},
    publisher = {PMLR},
    year = {2025},
}

Standard Link prediction benchmarks contain an inherent bias favoring high-degree nodes, allowing simple degree-based methods to achieve near-optimal results. We introduce a degree-corrected variant of the task that provides fairer evaluation and better alignment with real-world recommendation performance. The revised benchmark improves model training by reducing overfitting to node degrees and enabling better learning of meaningful graph structures.