paper-with-me

홈 › Papers

Masked Graph Transformer for Large-Scale Recommendation

2024-05-07 · Huiyuan Chen, Zhe Xu, Chin-Chia Michael Yeh, Vivian Lai, Yan Zheng, Minghua Xu, Hanghang Tong

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.

📄 PDF Abstract BibTeX arXiv:2405.04028

Code (0)

등록된 구현이 없습니다.

Methods 이 논문이 사용한 방법론

Attention 설명 없음
LapEigen 설명 없음
Laplacian PE Laplacian eigenvectors represent a natural generalization of the…
Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…
Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…
Residual Connection 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Position-Wise Feed-Forward Layer 설명 없음

Similar Papers 제목 키워드 기반

Color Recommendation for Vector Graphic Documents based on Multi-Palette Representation

2022-09-22 · Qianru Qiu, Xueting Wang, Mayu Otani, Yuki Iwazaki

Vector graphic documents present multiple visual elements, such as images, shapes, and texts. Choosing appropriate colors for multiple visual elements is a difficult but crucial task for both amateurs and professional de…

Heterogeneous Graph Masked Contrastive Learning for Robust Recommendation

2025-05-30 · Lei Sang, Yu Wang, Yiwen Zhang

Heterogeneous graph neural networks (HGNNs) have demonstrated their superiority in exploiting auxiliary information for recommendation tasks. However, graphs constructed using meta-paths in HGNNs are usually too dense an…

Contrastive Learning

Optimizing Encoder-Only Transformers for Session-Based Recommendation Systems

2024-10-15 · Anis Redjdal, Luis Pinto, Michel Desmarais

Session-based recommendation is the task of predicting the next item a user will interact with, often without access to historical user data. In this work, we introduce Sequential Masked Modeling, a novel approach for en…

Data AugmentationRecommendation SystemsSession-Based Recommendations

Pre-training Graph Transformer with Multimodal Side Information for Recommendation

2020-10-23 · Yong liu, Susen Yang, Chenyi Lei, Guoxin Wang 외

Side information of items, e.g., images and text description, has shown to be effective in contributing to accurate recommendations. Inspired by the recent success of pre-training models on natural language and images, w…

Recommendation SystemsUnsupervised Pre-training

Graph Masked Autoencoder for Sequential Recommendation

2023-05-08 · Yaowen Ye, Lianghao Xia, Chao Huang

While some powerful neural network architectures (e.g., Transformer, Graph Neural Networks) have achieved improved performance in sequential recommendation with high-order item dependency modeling, they may suffer from p…

Contrastive LearningData AugmentationRecommendation SystemsSequential Recommendation