# Masked Graph Transformer for Large-Scale Recommendation

arXiv: https://arxiv.org/abs/2405.04028 · HTML: https://mlsanity.com/paper/2405.04028/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 May 2024.

## Built on by (most cited first, 5 of 5)

- [A Survey of Graph Transformers: Architectures, Theories and Applications](https://mlsanity.com/paper/2502.16533/) (2025)
- [Linear Transformer Topological Masking with Graph Random Features](https://mlsanity.com/paper/2410.03462/) (2024)
- [How to Make LMs Strong Node Classifiers?](https://mlsanity.com/paper/2410.02296/) (2024)
- [FairGE: Fairness-Aware Graph Encoding in Incomplete Social Networks](https://mlsanity.com/paper/2601.09394/) (2026)
- [Rotary Position Encodings for Graphs](https://mlsanity.com/paper/2509.22259/) (2025)

## Abstract (arXiv)

Graph Transformers have garnered significant attention for learning graph-structured data, thanks to their superb ability to capture long-range dependencies among nodes. However, the quadratic space and time complexity hinders the scalability of Graph Transformers, particularly for large-scale recommendation. Here we propose an efficient Masked Graph Transformer, named MGFormer, capable of capturing all-pair interactions among nodes with a linear complexity. To achieve this, we treat all user/item nodes as independent tokens, enhance them with positional embeddings, and feed them into a kernelized attention module. Additionally, we incorporate learnable relative degree information to appropriately reweigh the attentions. Experimental results show the superior performance of our MGFormer, even with a single attention layer.