Federated Adaptation for Foundation Model-based Recommendations

Authors: Chunxu Zhang, Guodong Long, Hongkuan Guo, Xiao Fang, Yang Song, Zhaojie Liu, Guorui Zhou, Zijian Zhang, Yang Liu, Bo Yang

IJCAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Experimental results on four benchmark datasets demonstrate our method s superior performance.
Researcher Affiliation Collaboration 1Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education, China 2College of Computer Science and Technology, Jilin University, China 3Australian Artificial Intelligence Institute, FEIT, University of Technology Sydney 4Kuaishou Technology 5Institute for AI Industry Research, Tsinghua University
Pseudocode No The paper does not contain any clearly labeled pseudocode or algorithm blocks.
Open Source Code Yes The code is available.1Code: https://github.com/Zhangcx19/IJCAI-24-Fed PA
Open Datasets Yes We evaluate Fed PA on four practical industrial recommendation datasets collected from the short video platform Kuaishou 2, i.e., Kuai Rand 3 (Kuai Rand-Pure and Kuai Randsmall) and Kuai SAR 4 (Kuai SAR-S and Kuai SAR-R).3https://kuairand.com/4https://kuaisar.github.io/
Dataset Splits Yes The dataset for the federated recommendation system is further split into train, validation, and test sets for each user based on interaction timestamps, with a ratio of 6:2:2.
Hardware Specification No The paper mentions 'deploying the pre-trained model on edge devices' and 'clients with limited computation capability' but does not provide specific hardware details such as GPU or CPU models used for running the experiments.
Software Dependencies No The paper does not specify versions for any software dependencies, libraries, or programming languages used in the experiments.
Experiment Setup No The paper describes dataset splits and evaluation protocols but does not provide specific hyperparameter values like learning rate, batch size, number of epochs, or optimizer settings for the experimental setup.