Robust Generalizable Heterogeneous Legal Link Prediction

TL;DR

This paper introduces robust methods for legal link prediction that enhance accuracy and generalizability across diverse legal systems by using edge dropout, feature concatenation, and multilingual node features with an improved decoder.

Contribution

The paper presents novel techniques including edge dropout, feature concatenation, and a multilingual node feature approach with an asymmetric decoder to improve legal link prediction robustness and transferability.

Findings

Error rates reduced by up to 45%

Enhanced generalization to disjoint legal systems

Improved inductive transferability

Abstract

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.