Personalized Collaborative Fine-Tuning for On-Device Large Language Models
We explore on-device self-supervised collaborative fine-tuning of large language models with limited local data availability. Taking inspiration from the collaborative learning community, we introduce three distinct trust-weighted gradient aggregation schemes: weight similarity-based, prediction similarity-based and validation performance-based. To minimize communication overhead, we integrate Low-Rank Adaptation (LoRA) and only exchange LoRA weight updates. Our protocols, driven by prediction and performance metrics, surpass both FedAvg and local fine-tuning methods, which is particularly evident in realistic scenarios with more diverse local data distributions. The results underscore the effectiveness of our approach in addressing heterogeneity and scarcity within local datasets.
Code (1)
Tasks
PredictionSimilar Papers 제목 키워드 기반
Flexible Personalized Split Federated Learning for On-Device Fine-Tuning of Foundation Models
Fine-tuning foundation models is critical for superior performance on personalized downstream tasks, compared to using pre-trained models. Collaborative learning can leverage local clients' datasets for fine-tuning, but …
Personalized Federated LearningDUET: A Tuning-Free Device-Cloud Collaborative Parameters Generation Framework for Efficient Device Model Generalization
Device Model Generalization (DMG) is a practical yet under-investigated research topic for on-device machine learning applications. It aims to improve the generalization ability of pre-trained models when deployed on res…
Device-Cloud CollaborationDomain AdaptationImage ClassificationModel Compression+1CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering
Personalized text generation has become crucial for adapting language models to diverse and evolving users' personal context across cultural, temporal, and contextual dimensions. While existing methods often rely on cent…
Text GenerationFed MobiLLM: Efficient Federated LLM Fine-Tuning over Heterogeneous Mobile Devices via Server Assisted Side-Tuning
Collaboratively fine-tuning (FT) large language models (LLMs) over heterogeneous mobile devices fosters immense potential applications of personalized intelligence. However, such a vision faces critical system challenges…
PocketLLM: Enabling On-Device Fine-Tuning for Personalized LLMs
Recent advancements in large language models (LLMs) have indeed showcased their impressive capabilities. On mobile devices, the wealth of valuable, non-public data generated daily holds great promise for locally fine-tun…