提出并行生成长语义ID的框架，提升推荐系统性能与效率
Generating Long Semantic IDs in Parallel for Recommendation
- 并行预测所有语义令牌，避免逐个生成的延迟
- 将语义ID长度扩展至64，NDCG@10平均提升12.6%
- 适合需要高效、高表达力推荐模型的场景
基于语义ID的推荐模型将每个物品分解为少量离散令牌以保留特定语义，从而提升性能、可扩展性和内存效率。尽管近期模型采用生成式方法，但通常依赖资源密集的束搜索和多次前向传播，导致推理效率低下，语义ID长度受限（如仅4个令牌），影响表达能力。为此，我们提出RPG，一种轻量级语义ID推荐框架。核心思想是生成无序长语义ID，使模型可并行预测所有令牌。通过多令牌预测损失训练模型，直接将语义融入学习目标。推理时构建相似语义ID图，引导解码以避免生成无效ID。实验表明，将语义ID长度扩展至64后，RPG在NDCG@10上平均优于生成基线12.6%，同时提升推理效率。代码已公开：https://github.com/facebookresearch/RPG_KDD2025。
原文摘要 · Abstract (English)
Semantic ID-based recommendation models tokenize each item into a small number of discrete tokens that preserve specific semantics, leading to better performance, scalability, and memory efficiency. While recent models adopt a generative approach, they often suffer from inefficient inference due to the reliance on resource-intensive beam search and multiple forward passes through the neural sequence model. As a result, the length of semantic IDs is typically restricted (e.g. to just 4 tokens), limiting their expressiveness. To address these challenges, we propose RPG, a lightweight framework for semantic ID-based recommendation. The key idea is to produce unordered, long semantic IDs, allowing the model to predict all tokens in parallel. We train the model to predict each token independently using a multi-token prediction loss, directly integrating semantics into the learning objective. During inference, we construct a graph connecting similar semantic IDs and guide decoding to avoid generating invalid IDs. Experiments show that scaling up semantic ID length to 64 enables RPG to outperform generative baselines by an average of 12.6% on the NDCG@10, while also improving inference efficiency. Code is available at: https://github.com/facebookresearch/RPG_KDD2025.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。