# NTSFormer: A Self-Teaching Graph Transformer for Multimodal Isolated Cold-Start Node Classification

arXiv: https://arxiv.org/abs/2507.04870 · HTML: https://mlsanity.com/paper/2507.04870/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in MoE for time series and graphs, one of 12 directions in Mixture-of-experts.
- Builds on 25 of its 40 references that are in the map.
- First posted on arXiv 7 Jul 2025.

## Placed in

- Mixture-of-experts / [MoE for time series and graphs](https://mlsanity.com/moe/moe-for-time-series-and-graphs/)

## Builds on (most cited first, 25 of 25)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity](https://mlsanity.com/paper/2101.03961/) (2021)
- [Recipe for a General, Powerful, Scalable Graph Transformer](https://mlsanity.com/paper/2205.12454/) (2022)
- [SIGN: Scalable Inception Graph Neural Networks](https://mlsanity.com/paper/2004.11198/) (2020)
- [NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification](https://mlsanity.com/paper/2306.08385/) (2023)
- [Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation](https://mlsanity.com/paper/2110.08727/) (2021)
- [NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs](https://mlsanity.com/paper/2206.04910/) (2022)
- [Polynormer: Polynomial-Expressive Graph Transformer in Linear Time](https://mlsanity.com/paper/2403.01232/) (2024)
- [VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs](https://mlsanity.com/paper/2308.02117/) (2023)
- [When Graph meets Multimodal: Benchmarking and Meditating on Multimodal Attributed Graphs Learning](https://mlsanity.com/paper/2410.09132/) (2024)
- [Efficient Heterogeneous Graph Learning via Random Projection](https://mlsanity.com/paper/2310.14481/) (2023)
- [A Multimodal Single-Branch Embedding Network for Recommendation in Cold-Start and Missing Modality Scenarios](https://mlsanity.com/paper/2409.17864/) (2024)
- [Gradient-Guided Modality Decoupling for Missing-Modality Robustness](https://mlsanity.com/paper/2402.16318/) (2024)
- [Training MLPs on Graphs without Supervision](https://mlsanity.com/paper/2412.03864/) (2024)
- [Do We Really Need to Drop Items with Missing Modalities in Multimodal Recommendation?](https://mlsanity.com/paper/2408.11767/) (2024)
- [Dealing with Missing Modalities in Multimodal Recommendation: a Feature Propagation-based Approach](https://mlsanity.com/paper/2403.19841/) (2024)
- [Enhancing Fake News Detection in Social Media via Label Propagation on Cross-modal Tweet Graph](https://mlsanity.com/paper/2406.09884/) (2024)
- [Enhancing Modality Representation and Alignment for Multimodal Cold-start Active Learning](https://mlsanity.com/paper/2412.09126/) (2024)

## Built on by (most cited first, 3 of 3)

- [OpenMAG: A Comprehensive Benchmark for Multimodal-Attributed Graph](https://mlsanity.com/paper/2602.05576/) (2026)
- [Cross-Modal Attention Network with Dual Graph Learning in Multimodal Recommendation](https://mlsanity.com/paper/2601.11151/) (2026)
- [GOMA: Toward Structure-Driven Multimodal Alignment from a Graph Signal Smoothing Perspective](https://mlsanity.com/paper/2605.15723/) (2026)

## Abstract (arXiv)

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's own features), and a "teacher" prediction incorporating both self and neighbor information. This enables the model to supervise itself without degrading to an MLP, thereby fully leveraging the Transformer's capacity to handle missing modalities. To handle diverse graph information and missing modalities, NTSFormer performs a one-time multimodal graph pre-computation that converts structural and feature data into token sequences, which are then processed by Mixture-of-Experts (MoE) Input Projection and Transformer layers for effective fusion. Experiments on public datasets show that NTSFormer achieves superior performance for multimodal isolated cold-start node classification.