NTSFormer: A Self-Teaching Graph Transformer for Multimodal Isolated Cold-Start Node Classification
Jun Hu, Yufei He, Yuan Li, Bryan Hooi, Bingsheng He
Abstract
Isolated cold-start node classification on multimodal graphs is challenging because such nodes have no edges and often have missing modalities (e.g., absent text or image features). Existing methods address structural isolation by degrading graph learning models to multilayer perceptrons (MLPs) for isolated cold-start inference, using a teacher model (with graph access) to guide the MLP. However, this results in limited model capacity in the student, which is further challenged when modalities are missing. In this paper, we propose Neighbor-to-Self Graph Transformer (NTSFormer), a unified Graph Transformer framework that jointly tackles the isolation and missing-modality issues via a self-teaching paradigm. Specifically, NTSFormer uses a cold-start attention mask to simultaneously make two predictions for each node: a "student" prediction based only on self information (i.e., the node
BibTeX
@inproceedings{aaai2026_ntsformeraselfte,
title = {NTSFormer: A Self-Teaching Graph Transformer for Multimodal Isolated Cold-Start Node Classification},
author = {Jun Hu and Yufei He and Yuan Li and Bryan Hooi and Bingsheng He},
booktitle = {AAAI 2026},
year = {2026}
}