Towards Efficient and Effective Adaptation of Large Language Models for Sequential Recommendation
Abstract: In recent years, with LLMs achieving state-of-the-art performance in context understanding, increasing efforts have been dedicated to developing LLM-enhanced sequential recommendation (SR) methods. Considering that most existing LLMs are not specifically optimized for recommendation tasks, adapting them for SR becomes a critical step in LLM-enhanced SR methods. Though numerous adaptation methods have been developed, it still remains a significant challenge to adapt LLMs for SR both efficiently and effectively. To address this challenge, in this paper, we introduce a novel side sequential network adaptation method, denoted as SSNA, for LLM enhanced SR. SSNA features three key designs to allow both efficient and effective LLM adaptation. First, SSNA learns adapters separate from LLMs, while fixing all the pre-trained parameters within LLMs to allow efficient adaptation. In addition, SSNA adapts the top-a layers of LLMs jointly, and integrates adapters sequentially for enhanced effectiveness (i.e., recommendation performance). We compare SSNA against five state-of-the-art baseline methods on five benchmark datasets using three LLMs. The experimental results demonstrate that SSNA significantly outperforms all the baseline methods in terms of recommendation performance, and achieves substantial improvement over the best-performing baseline methods at both run-time and memory efficiency during training. Our analysis shows the effectiveness of integrating adapters in a sequential manner. Our parameter study demonstrates the effectiveness of jointly adapting the top-a layers of LLMs.
- Bhattacharyya, M. 2022. Gradient Accumulation: Overcoming Memory Constraints in Deep Learning. https://towardsdatascience.com/gradient-accumulation-overcoming-memory-constraints-in-deep-learning-36d411252d01.
- Towards understanding mixture of experts in deep learning. arXiv preprint arXiv:2208.02813.
- Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805.
- Sequential recommendation via stochastic self-attention. In Proceedings of the ACM Web Conference 2022, 2036–2047.
- Towards a unified view of parameter-efficient transfer learning. arXiv preprint arXiv:2110.04366.
- Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition, 770–778.
- Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering. In proceedings of the 25th international conference on world wide web, 507–517.
- Session-based recommendations with recurrent neural networks. arXiv preprint arXiv:1511.06939.
- Towards universal sequence representation learning for recommender systems. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 585–593.
- Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685.
- Whiteningbert: An easy unsupervised sentence embedding approach. arXiv preprint arXiv:2104.01767.
- Self-attentive sequential recommendation. In 2018 IEEE international conference on data mining (ICDM), 197–206. IEEE.
- Make Your Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning. arXiv preprint arXiv:2306.00477.
- Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692.
- Hierarchical gating networks for sequential recommendation. In Proceedings of the 25th ACM SIGKDD international conference on knowledge discovery & data mining, 825–833.
- PEFT: State-of-the-art Parameter-Efficient Fine-Tuning methods. https://github.com/huggingface/peft.
- OpenAI. 2023. GPT-4 Technical Report. ArXiv, abs/2303.08774.
- HAM: Hybrid Associations Models for Sequential Recommendation. IEEE Transactions on Knowledge and Data Engineering, 34(10): 4838–4853.
- DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv:1910.01108.
- Outrageously large neural networks: The sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:1701.06538.
- Understanding the role of self attention for efficient speech recognition. In International Conference on Learning Representations.
- Personalized top-n sequential recommendation via convolutional sequence embedding. In Proceedings of the eleventh ACM international conference on web search and data mining, 565–573.
- Well-read students learn better: On the importance of pre-training compact models. arXiv preprint arXiv:1908.08962.
- Attention is all you need. Advances in neural information processing systems, 30.
- TransRec: Learning Transferable Recommendation from Mixture-of-Modality Feedback. arXiv preprint arXiv:2206.06190.
- Transformers: State-of-the-Art Natural Language Processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, 38–45. Online: Association for Computational Linguistics.
- Where to go next for recommender systems? id-vs. modality-based recommender models revisited. arXiv preprint arXiv:2303.13835.
- Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models. arXiv preprint arXiv:2106.10199.
- Adaptive budget allocation for parameter-efficient fine-tuning. arXiv preprint arXiv:2303.10512.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
