相关论文: FedPOB: Sample-Efficient Federated Prompt Optimiza…

Large Language Models (LLMs) have achieved great success in many real-world applications, especially the one serving as the cognitive backbone of Multi-Agent Systems (MAS) to orchestrate complex workflows in practice. Since many deployment…

Federated optimization studies the problem of collaborative function optimization among multiple clients (e.g. mobile devices or organizations) under the coordination of a central server. Since the data is collected separately by each…

Bandit optimization usually refers to the class of online optimization problems with limited feedback, namely, a decision maker uses only the objective value at the current point to make a new decision and does not have access to the…

Federated multi-armed bandits (FMAB) is a new bandit paradigm that parallels the federated learning (FL) framework in supervised learning. It is inspired by practical applications in cognitive radio and recommender systems, and enjoys…

Pre-trained language models (PLM) have revolutionized the NLP landscape, achieving stellar performances across diverse tasks. These models, while benefiting from vast training data, often require fine-tuning on specific data to cater to…

A general framework of personalized federated multi-armed bandits (PF-MAB) is proposed, which is a new bandit paradigm analogous to the federated learning (FL) framework in supervised learning and enjoys the features of FL with…

Prompt engineering has become central to eliciting the capabilities of large language models (LLMs). At its core lies prompt selection -- efficiently identifying the most effective prompts. However, most prior investigations overlook a key…

The contextual multi-armed bandit (MAB) is a widely used framework for problems requiring sequential decision-making under uncertainty, such as recommendation systems. In applications involving a large number of users, the performance of…

This paper considers the contextual multi-armed bandit (CMAB) problem with fairness and privacy guarantees in a federated environment. We consider merit-based exposure as the desired fair outcome, which provides exposure to each action in…

Multi-armed bandits (MAB) provide a principled online learning approach to attain the balance between exploration and exploitation. Due to the superior performance and low feedback learning without the learning to act in multiple…

Large language models (LLMs) have recently been employed as agents to solve sequential decision-making tasks such as Bayesian optimization and multi-armed bandits (MAB). These works usually adopt an LLM for sequential action selection by…

Federated learning has emerged as an innovative paradigm of collaborative machine learning. Unlike conventional machine learning, a global model is collaboratively learned while data remains distributed over a tremendous number of client…

The rapid proliferation of decentralized learning systems mandates the need for differentially-private cooperative learning. In this paper, we study this in context of the contextual linear bandit: we consider a collection of agents…

Prompt learning in pretrained visual-language models has shown remarkable flexibility across various downstream tasks. Leveraging its inherent lightweight nature, recent research attempted to integrate the powerful pretrained models into…

Multi-armed bandits (MAB) is a sequential decision-making model in which the learner controls the trade-off between exploration and exploitation to maximize its cumulative reward. Federated multi-armed bandits (FMAB) is an emerging…

The remarkable instruction-following capability of large language models (LLMs) has sparked a growing interest in automatically finding good prompts, i.e., prompt optimization. Most existing works follow the scheme of selecting from a…

Federated Recommendation Systems (FRS) enable privacy-preserving model training by keeping user data on edge devices. However, the practical deployment of FRS in Edge-Cloud environments faces significant challenges due to system and…

Conversational recommender systems have emerged as a potent solution for efficiently eliciting user preferences. These systems interactively present queries associated with "key terms" to users and leverage user feedback to estimate user…

Contextual multi-armed bandit (MAB) is an important sequential decision-making problem in recommendation systems. A line of works, called the clustering of bandits (CLUB), utilize the collaborative effect over users and dramatically improve…

Prompt optimization aims to search for effective prompts that enhance the performance of large language models (LLMs). Although existing prompt optimization methods have discovered effective prompts, they often differ from sophisticated…