Multimodal foundation models are transformative in sequential recommender systems, leveraging powerful representation learning capabilities. While Parameter-efficient Fine-tuning (PEFT) is commonly used to adapt foundation models for recommendation tasks, most research prioritizes parameter efficiency, often overlooking critical factors like GPU memory efficiency and training speed. Addressing this gap, our paper introduces IISAN (Intra- and Inter-modal Side Adapted Network for Multimodal Representation), a simple plug-and-play architecture using a Decoupled PEFT structure and exploiting both intra- and inter-modal adaptation. IISAN matches the performance of full fine-tuning (FFT) and state-of-the-art PEFT. More importantly, it significantly reduces GPU memory usage - from 47GB to just 3GB for multimodal sequential recommendation tasks. Additionally, it accelerates training time per epoch from 443s to 22s compared to FFT. This is also a notable improvement over the Adapter and LoRA, which require 37-39 GB GPU memory and 350-380 seconds per epoch for training. Furthermore, we propose a new composite efficiency metric, TPME (Training-time, Parameter, and GPU Memory Efficiency) to alleviate the prevalent misconception that "parameter efficiency represents overall efficiency". TPME provides more comprehensive insights into practical efficiency comparisons between different methods. Besides, we give an accessible efficiency analysis of all PEFT and FFT approaches, which demonstrate the superiority of IISAN. We release our codes and other materials at https://github.com/GAIR-Lab/IISAN.

翻译：多模态基础模型凭借强大的表示学习能力，在序列推荐系统中具有变革性作用。尽管参数高效微调（PEFT）常用于将基础模型适配至推荐任务，但多数研究优先考虑参数效率，往往忽略了GPU内存效率与训练速度等关键因素。针对这一空白，本文提出IISAN（面向多模态表示的模态内与模态间侧适配网络），这是一种采用解耦PEFT结构的即插即用架构，同时利用模态内与模态间适配。IISAN在性能上与全参数微调（FFT）及当前最优的PEFT方法相当。更重要的是，它将多模态序列推荐任务的GPU内存占用从47GB显著降至3GB，并将每轮训练时间从443秒加速至22秒。相比Adapter和LoRA（需37-39GB GPU内存、每轮训练350-380秒），这也是显著改进。此外，我们提出新的复合效率指标TPME（训练时间、参数与GPU内存效率），以缓解"参数效率代表整体效率"这一普遍误解。TPME为不同方法间的实际效率对比提供了更全面的洞察。同时，我们对所有PEFT与FFT方法进行了简便的效率分析，证明了IISAN的优越性。相关代码与资料已发布在https://github.com/GAIR-Lab/IISAN。