Rankformer: A Graph Transformer for Recommendation based on Ranking Objective

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Sirui, Han, Shen, Chen, Jiawei, Hu, Binbin, Zhou, Sheng, Wang, Gang, Feng, Yan, Chen, Chun, Wang, Can
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915208016953344
author Chen, Sirui
Han, Shen
Chen, Jiawei
Hu, Binbin
Zhou, Sheng
Wang, Gang
Feng, Yan
Chen, Chun
Wang, Can
author_facet Chen, Sirui
Han, Shen
Chen, Jiawei
Hu, Binbin
Zhou, Sheng
Wang, Gang
Feng, Yan
Chen, Chun
Wang, Can
contents Recommender Systems (RS) aim to generate personalized ranked lists for each user and are evaluated using ranking metrics. Although personalized ranking is a fundamental aspect of RS, this critical property is often overlooked in the design of model architectures. To address this issue, we propose Rankformer, a ranking-inspired recommendation model. The architecture of Rankformer is inspired by the gradient of the ranking objective, embodying a unique (graph) transformer architecture -- it leverages global information from all users and items to produce more informative representations and employs specific attention weights to guide the evolution of embeddings towards improved ranking performance. We further develop an acceleration algorithm for Rankformer, reducing its complexity to a linear level with respect to the number of positive instances. Extensive experimental results demonstrate that Rankformer outperforms state-of-the-art methods. The code is available at https://github.com/StupidThree/Rankformer.
format Preprint
id arxiv_https___arxiv_org_abs_2503_16927
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Rankformer: A Graph Transformer for Recommendation based on Ranking Objective
Chen, Sirui
Han, Shen
Chen, Jiawei
Hu, Binbin
Zhou, Sheng
Wang, Gang
Feng, Yan
Chen, Chun
Wang, Can
Information Retrieval
Recommender Systems (RS) aim to generate personalized ranked lists for each user and are evaluated using ranking metrics. Although personalized ranking is a fundamental aspect of RS, this critical property is often overlooked in the design of model architectures. To address this issue, we propose Rankformer, a ranking-inspired recommendation model. The architecture of Rankformer is inspired by the gradient of the ranking objective, embodying a unique (graph) transformer architecture -- it leverages global information from all users and items to produce more informative representations and employs specific attention weights to guide the evolution of embeddings towards improved ranking performance. We further develop an acceleration algorithm for Rankformer, reducing its complexity to a linear level with respect to the number of positive instances. Extensive experimental results demonstrate that Rankformer outperforms state-of-the-art methods. The code is available at https://github.com/StupidThree/Rankformer.
title Rankformer: A Graph Transformer for Recommendation based on Ranking Objective
topic Information Retrieval
url https://arxiv.org/abs/2503.16927