Customizing Language Models with Instance-wise LoRA for Sequential Recommendation

• URL: http://arxiv.org/abs/2408.10159v3
• Date: Fri, 1 Nov 2024 03:47:59 GMT
• Title: Customizing Language Models with Instance-wise LoRA for Sequential Recommendation
• Authors: Xiaoyu Kong, Jiancan Wu, An Zhang, Leheng Sheng, Hui Lin, Xiang Wang, Xiangnan He,
• Abstract summary: Sequential recommendation systems predict the next interaction item based on users' past interactions, aligning recommendations with individual preferences. We propose Instance-wise LoRA (iLoRA) as a form of multi-task learning, integrating LoRA with the Mixture of Experts (MoE) framework. iLoRA achieves an average relative improvement of 11.4% over basic LoRA in the hit ratio metric, with less than a 1% relative increase in trainable parameters.
• Score: 28.667247613039965
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Sequential recommendation systems predict the next interaction item based on users' past interactions, aligning recommendations with individual preferences. Leveraging the strengths of Large Language Models (LLMs) in knowledge comprehension and reasoning, recent approaches are eager to apply LLMs to sequential recommendation. A common paradigm is converting user behavior sequences into instruction data, and fine-tuning the LLM with parameter-efficient fine-tuning (PEFT) methods like Low-Rank Adaption (LoRA). However, the uniform application of LoRA across diverse user behaviors is insufficient to capture individual variability, resulting in negative transfer between disparate sequences. To address these challenges, we propose Instance-wise LoRA (iLoRA). We innovatively treat the sequential recommendation task as a form of multi-task learning, integrating LoRA with the Mixture of Experts (MoE) framework. This approach encourages different experts to capture various aspects of user behavior. Additionally, we introduce a sequence representation guided gate function that generates customized expert participation weights for each user sequence, which allows dynamic parameter adjustment for instance-wise recommendations. In sequential recommendation, iLoRA achieves an average relative improvement of 11.4\% over basic LoRA in the hit ratio metric, with less than a 1\% relative increase in trainable parameters. Extensive experiments on three benchmark datasets demonstrate the effectiveness of iLoRA, highlighting its superior performance compared to existing methods in mitigating negative transfer and improving recommendation accuracy. Our data and code are available at https://github.com/AkaliKong/iLoRA.

Related papers

• Large Language Model Empowered Embedding Generator for Sequential Recommendation [57.49045064294086]
  Large Language Model (LLM) has the potential to understand the semantic connections between items, regardless of their popularity. We present LLMEmb, an innovative technique that harnesses LLM to create item embeddings that bolster the performance of Sequential Recommender Systems.
  arXiv  Detail & Related papers  (2024-09-30T03:59:06Z)
• Unleash LLMs Potential for Recommendation by Coordinating Twin-Tower Dynamic Semantic Token Generator [60.07198935747619]
  We propose Twin-Tower Dynamic Semantic Recommender (T TDS), the first generative RS which adopts dynamic semantic index paradigm. To be more specific, we for the first time contrive a dynamic knowledge fusion framework which integrates a twin-tower semantic token generator into the LLM-based recommender. The proposed T TDS recommender achieves an average improvement of 19.41% in Hit-Rate and 20.84% in NDCG metric, compared with the leading baseline methods.
  arXiv  Detail & Related papers  (2024-09-14T01:45:04Z)
• Laser: Parameter-Efficient LLM Bi-Tuning for Sequential Recommendation with Collaborative Information [76.62949982303532]
  We propose a parameter-efficient Large Language Model Bi-Tuning framework for sequential recommendation with collaborative information (Laser) In our Laser, the prefix is utilized to incorporate user-item collaborative information and adapt the LLM to the recommendation task, while the suffix converts the output embeddings of the LLM from the language space to the recommendation space for the follow-up item recommendation. M-Former is a lightweight MoE-based querying transformer that uses a set of query experts to integrate diverse user-specific collaborative information encoded by frozen ID-based sequential recommender systems.
  arXiv  Detail & Related papers  (2024-09-03T04:55:03Z)
• Lifelong Personalized Low-Rank Adaptation of Large Language Models for Recommendation [50.837277466987345]
  We focus on the field of large language models (LLMs) for recommendation. We propose RecLoRA, which incorporates a Personalized LoRA module that maintains independent LoRAs for different users. We also design a Few2Many Learning Strategy, using a conventional recommendation model as a lens to magnify small training spaces to full spaces.
  arXiv  Detail & Related papers  (2024-08-07T04:20:28Z)
• SARA: Singular-Value Based Adaptive Low-Rank Adaption [4.135688713311511]
  LoRA as a parameter-efficient fine-tuning(PEFT) method is widely used for not adding inference overhead. In this work, we first analyze the relationship between the performance of different layers and their ranks using SVD. Based on this, we design the Singular-Value Based Adaptive Low-Rank Adaption(SARA)
  arXiv  Detail & Related papers  (2024-08-06T16:39:42Z)
• Semantic Codebook Learning for Dynamic Recommendation Models [55.98259490159084]
  Dynamic sequential recommendation (DSR) can generate model parameters based on user behavior to improve personalization of sequential recommendation. It faces the challenges of large parameter search space and sparse and noisy user-item interactions, which reduces the applicability of the generated model parameters. The Semantic Codebook Learning for Dynamic Recommendation Models (SOLID) framework presents a significant advancement in DSR by effectively tackling these challenges.
  arXiv  Detail & Related papers  (2024-07-31T19:25:25Z)
• Relative Preference Optimization: Enhancing LLM Alignment through Contrasting Responses across Identical and Diverse Prompts [95.09994361995389]
  Relative Preference Optimization (RPO) is designed to discern between more and less preferred responses derived from both identical and related prompts. RPO has demonstrated a superior ability to align large language models with user preferences and to improve their adaptability during the training process.
  arXiv  Detail & Related papers  (2024-02-12T22:47:57Z)
• Sequence Adaptation via Reinforcement Learning in Recommender Systems [8.909115457491522]
  We propose the SAR model, which learns the sequential patterns and adjusts the sequence length of user-item interactions in a personalized manner. In addition, we optimize a joint loss function to align the accuracy of the sequential recommendations with the expected cumulative rewards of the critic network. Our experimental evaluation on four real-world datasets demonstrates the superiority of our proposed model over several baseline approaches.
  arXiv  Detail & Related papers  (2021-07-31T13:56:46Z)
• A Hybrid Bandit Framework for Diversified Recommendation [42.516774050676254]
  We propose the Linear Modular Dispersion Bandit (LMDB) framework for optimizing a combination of modular functions and dispersion functions. Specifically, LMDB employs modular functions to model the relevance properties of each item, and dispersion functions to describe the diversity properties of an item set. We also develop a learning algorithm, called Linear Modular Dispersion Hybrid (LMDH), to solve the LMDB problem and derive a gap-free bound on its n-step regret.
  arXiv  Detail & Related papers  (2020-12-24T13:24:40Z)

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.