CoS: Towards Optimal Event Scheduling via Chain-of-Scheduling

TL;DR

This paper introduces CoS, a framework that leverages Large Language Models to optimize event scheduling in social networks by breaking down the task into stages, achieving near-optimal effectiveness efficiently and with strong zero-shot capabilities.

Contribution

The paper presents a novel Chain-of-Scheduling framework that activates LLMs for event scheduling, formulated into atomic stages and trained via Knowledge Distillation, addressing efficiency and effectiveness trade-offs.

Findings

Achieves near-theoretical optimal effectiveness

Demonstrates high efficiency on real-world datasets

Shows strong zero-shot learning ability

Abstract

Recommending event schedules is a key issue in Event-based Social Networks (EBSNs) in order to maintain user activity. An effective recommendation is required to maximize the user's preference, subjecting to both time and geographical constraints. Existing methods face an inherent trade-off among efficiency, effectiveness, and generalization, due to the NP-hard nature of the problem. This paper proposes the Chain-of-Scheduling (CoS) framework, which activates the event scheduling capability of Large Language Models (LLMs) through a guided, efficient scheduling process. CoS enhances LLM by formulating the schedule task into three atomic stages, i.e., exploration, verification and integration. Then we enable the LLMs to generate CoS autonomously via Knowledge Distillation (KD). Experimental results show that CoS achieves near-theoretical optimal effectiveness with high efficiency on three real-world datasets in a interpretable manner. Moreover, it demonstrates strong zero-shot learning ability on out-of-domain data.