Implicit degree bias in the link prediction task

May 23, 2024 Β· Declared Dead Β· πŸ› International Conference on Machine Learning

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Rachith Aiyappa, Xin Wang, Munjung Kim, Ozgur Can Seckin, Jisung Yoon, Yong-Yeol Ahn, Sadamori Kojaku arXiv ID 2405.14985 Category cs.SI: Social & Info Networks Cross-listed physics.soc-ph Citations 4 Venue International Conference on Machine Learning Last Checked 4 months ago
Abstract
Link prediction -- a task of distinguishing actual hidden edges from random unconnected node pairs -- is one of the quintessential tasks in graph machine learning. Despite being widely accepted as a universal benchmark and a downstream task for representation learning, the validity of the link prediction benchmark itself has been rarely questioned. Here, we show that the common edge sampling procedure in the link prediction task has an implicit bias toward high-degree nodes and produces a highly skewed evaluation that favors methods overly dependent on node degree, to the extent that a ``null'' link prediction method based solely on node degree can yield nearly optimal performance. We propose a degree-corrected link prediction task that offers a more reasonable assessment that aligns better with the performance in the recommendation task. Finally, we demonstrate that the degree-corrected benchmark can more effectively train graph machine-learning models by reducing overfitting to node degrees and facilitating the learning of relevant structures in graphs.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Social & Info Networks

Died the same way β€” πŸ‘» Ghosted