arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2405.04028cs.IR
收藏

用于大规模推荐的掩码图Transformer

Masked Graph Transformer for Large-Scale Recommendation

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

AI总结:

本文提出线性复杂度的掩码图Transformer模型MGFormer,通过核化注意力和可学习相对度信息高效捕捉全对节点交互,在大规模推荐中仅用单层注意力即取得优越性能。

摘要:

图Transformer因其出色的捕捉节点间长程依赖能力,在学习图结构数据方面获得了广泛关注。然而,二次方的空间和时间复杂度阻碍了图Transformer的可扩展性,尤其是在大规模推荐场景中。为此,我们提出了一种高效的掩码图Transformer,名为MGFormer,能够以线性复杂度捕捉节点间的全对交互。为实现这一目标,我们将所有用户/物品节点视为独立的token,为其添加位置嵌入,并将其输入核化注意力模块。此外,我们引入了可学习的相对度信息来适当地重新加权注意力。实验结果表明,即使仅使用单个注意力层,我们的MGFormer也展现出优越的性能。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑