The authors formalize a leave-one-domain-out protocol in which a model is self-supervised on several source domains, then evaluated on labeled future interactions from a held-out domain.
Semantic alignment improves edge classification across unseen dynamic graph domains
A leave-one-domain-out evaluation finds that existing dynamic-graph models transfer poorly, while aligning temporal and structural signals with pretrained textual representations improves performance.
Top University
Tyler Bonnet · Marek Rei
Imperial College London
Research Digest··2 min read
Bonnet and Rei introduce a transfer-learning protocol for classifying future interactions in dynamic text-attributed graphs from previously unseen domains.
Why this paper
From Imperial College London
In one line
Spatio-Temporal Semantic Alignment outperforms all existing methods on edge classification for dynamic text-attributed graphs.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§