Mini-Batch Class Composition Bias in Link Prediction
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911630169735168 |
|---|---|
| author | Maguire, Kieran Dasmahapatra, Srinandan |
| author_facet | Maguire, Kieran Dasmahapatra, Srinandan |
| contents | Prior work on node classification has shown that Graph Neural Networks (GNNs) can learn representations that transfer across graphs, when underlying graph properties are shared. For a fixed graph, one would then expect GNNs trained for link prediction to learn a representation consistent with that learnt for node classification. We show this intuition does not hold in the general case. Instead, we find popular link prediction models can learn a trivial mini-batch dependent heuristic, enabled by batch-normalisation layers, to solve the edge classification task. When correcting for this, we observe increased alignment of the network representation with node-class relevant features, suggesting the network has learnt a graph representation that better aligns with the underlying graph's properties. Our findings suggest that standard link prediction training may be leading us to overestimate link predictors' ability to learn a generalised representation of a graph that is consistent across tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_25978 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Mini-Batch Class Composition Bias in Link Prediction Maguire, Kieran Dasmahapatra, Srinandan Machine Learning Artificial Intelligence Prior work on node classification has shown that Graph Neural Networks (GNNs) can learn representations that transfer across graphs, when underlying graph properties are shared. For a fixed graph, one would then expect GNNs trained for link prediction to learn a representation consistent with that learnt for node classification. We show this intuition does not hold in the general case. Instead, we find popular link prediction models can learn a trivial mini-batch dependent heuristic, enabled by batch-normalisation layers, to solve the edge classification task. When correcting for this, we observe increased alignment of the network representation with node-class relevant features, suggesting the network has learnt a graph representation that better aligns with the underlying graph's properties. Our findings suggest that standard link prediction training may be leading us to overestimate link predictors' ability to learn a generalised representation of a graph that is consistent across tasks. |
| title | Mini-Batch Class Composition Bias in Link Prediction |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2604.25978 |