Saved in:
Bibliographic Details
Main Authors: Wendlinger, Lorenz, Nonn, Simon Alexander, Zubaer, Abdullah Al, Granitzer, Michael
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2602.04812
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917248263782400
author Wendlinger, Lorenz
Nonn, Simon Alexander
Zubaer, Abdullah Al
Granitzer, Michael
author_facet Wendlinger, Lorenz
Nonn, Simon Alexander
Zubaer, Abdullah Al
Granitzer, Michael
contents Recent work has applied link prediction to large heterogeneous legal citation networks \new{with rich meta-features}. We find that this approach can be improved by including edge dropout and feature concatenation for the learning of more robust representations, which reduces error rates by up to 45%. We also propose an approach based on multilingual node features with an improved asymmetric decoder for compatibility, which allows us to generalize and extend the prediction to more, geographically and linguistically disjoint, data from New Zealand. Our adaptations also improve inductive transferability between these disjoint legal systems.
format Preprint
id arxiv_https___arxiv_org_abs_2602_04812
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Robust Generalizable Heterogeneous Legal Link Prediction
Wendlinger, Lorenz
Nonn, Simon Alexander
Zubaer, Abdullah Al
Granitzer, Michael
Machine Learning
Information Retrieval
Recent work has applied link prediction to large heterogeneous legal citation networks \new{with rich meta-features}. We find that this approach can be improved by including edge dropout and feature concatenation for the learning of more robust representations, which reduces error rates by up to 45%. We also propose an approach based on multilingual node features with an improved asymmetric decoder for compatibility, which allows us to generalize and extend the prediction to more, geographically and linguistically disjoint, data from New Zealand. Our adaptations also improve inductive transferability between these disjoint legal systems.
title Robust Generalizable Heterogeneous Legal Link Prediction
topic Machine Learning
Information Retrieval
url https://arxiv.org/abs/2602.04812