Learnable Item Tokenization for Generative Recommendation
- URL: http://arxiv.org/abs/2405.07314v2
- Date: Mon, 19 Aug 2024 02:21:17 GMT
- Title: Learnable Item Tokenization for Generative Recommendation
- Authors: Wenjie Wang, Honghui Bao, Xinyu Lin, Jizhi Zhang, Yongqi Li, Fuli Feng, See-Kiong Ng, Tat-Seng Chua,
- Abstract summary: We propose LETTER (a LEarnable Tokenizer for generaTivE Recommendation), which integrates hierarchical semantics, collaborative signals, and code assignment diversity.
LETTER incorporates Residual Quantized VAE for semantic regularization, a contrastive alignment loss for collaborative regularization, and a diversity loss to mitigate code assignment bias.
- Score: 78.30417863309061
- License:
- Abstract: Utilizing powerful Large Language Models (LLMs) for generative recommendation has attracted much attention. Nevertheless, a crucial challenge is transforming recommendation data into the language space of LLMs through effective item tokenization. Current approaches, such as ID, textual, and codebook-based identifiers, exhibit shortcomings in encoding semantic information, incorporating collaborative signals, or handling code assignment bias. To address these limitations, we propose LETTER (a LEarnable Tokenizer for generaTivE Recommendation), which integrates hierarchical semantics, collaborative signals, and code assignment diversity to satisfy the essential requirements of identifiers. LETTER incorporates Residual Quantized VAE for semantic regularization, a contrastive alignment loss for collaborative regularization, and a diversity loss to mitigate code assignment bias. We instantiate LETTER on two models and propose a ranking-guided generation loss to augment their ranking ability theoretically. Experiments on three datasets validate the superiority of LETTER, advancing the state-of-the-art in the field of LLM-based generative recommendation.
Related papers
- EAGER-LLM: Enhancing Large Language Models as Recommenders through Exogenous Behavior-Semantic Integration [60.47645731801866]
Large language models (LLMs) are increasingly leveraged as foundational backbones in advanced recommender systems.
LLMs are pre-trained linguistic semantics but learn collaborative semantics from scratch via the llm-Backbone.
We propose EAGER-LLM, a decoder-only generative recommendation framework that integrates endogenous and endogenous behavioral and semantic information in a non-intrusive manner.
arXiv Detail & Related papers (2025-02-20T17:01:57Z) - Order-agnostic Identifier for Large Language Model-based Generative Recommendation [94.37662915542603]
Items are assigned identifiers for Large Language Models (LLMs) to encode user history and generate the next item.
Existing approaches leverage either token-sequence identifiers, representing items as discrete token sequences, or single-token identifiers, using ID or semantic embeddings.
We propose SETRec, which leverages semantic tokenizers to obtain order-agnostic multi-dimensional tokens.
arXiv Detail & Related papers (2025-02-15T15:25:38Z) - Semantic Convergence: Harmonizing Recommender Systems via Two-Stage Alignment and Behavioral Semantic Tokenization [10.47505806629852]
Large language models (LLMs) are adept at discerning profound user interests from historical behaviors.
We propose a novel framework that harmoniously merges traditional recommendation models with the prowess of LLMs.
We design a series of specialized supervised learning tasks aimed at aligning collaborative signals with the subtleties of natural language semantics.
arXiv Detail & Related papers (2024-12-18T12:07:58Z) - Break the ID-Language Barrier: An Adaption Framework for Sequential Recommendation [10.305878081909743]
We propose IDLE-Adapter, a framework that integrates pre-trained ID embeddings, rich in domain-specific knowledge, into large language models.
IDLE-Adapter acts as a bridge, transforming sparse user-item interaction data into dense, LLM-compatible representations.
arXiv Detail & Related papers (2024-11-27T11:59:44Z) - Towards Scalable Semantic Representation for Recommendation [65.06144407288127]
Mixture-of-Codes is proposed to construct semantic IDs based on large language models (LLMs)
Our method achieves superior discriminability and dimension robustness scalability, leading to the best scale-up performance in recommendations.
arXiv Detail & Related papers (2024-10-12T15:10:56Z) - Decoding Matters: Addressing Amplification Bias and Homogeneity Issue for LLM-based Recommendation [32.85339480783571]
We introduce a new decoding approach named Debiasing-Diversifying Decoding (D3)
D3 disables length normalization for ghost tokens to alleviate amplification bias.
Experiments on real-world datasets demonstrate the method's effectiveness.
arXiv Detail & Related papers (2024-06-21T06:47:28Z) - EAGER: Two-Stream Generative Recommender with Behavior-Semantic Collaboration [63.112790050749695]
We introduce EAGER, a novel generative recommendation framework that seamlessly integrates both behavioral and semantic information.
We validate the effectiveness of EAGER on four public benchmarks, demonstrating its superior performance compared to existing methods.
arXiv Detail & Related papers (2024-06-20T06:21:56Z) - Contrastive Decoding Improves Reasoning in Large Language Models [55.16503283583076]
We show that Contrastive Decoding achieves large out-of-the-box improvements over greedy decoding on a variety of reasoning tasks.
We show that Contrastive Decoding leads LLaMA-65B to outperform LLaMA 2, GPT-3.5 and PaLM 2-L on the HellaSwag commonsense reasoning benchmark.
arXiv Detail & Related papers (2023-09-17T00:29:32Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.