TrimCaching: Parameter-sharing AI Model Caching in Wireless Edge Networks

TL;DR

This paper introduces TrimCaching, a novel parameter-sharing model caching scheme for wireless edge networks that enhances storage efficiency and reduces latency by sharing model parameters across AI models.

Contribution

It formulates a parameter-sharing cache placement problem, analyzes its complexity, and develops approximation algorithms for both special and general cases.

Findings

Significant improvement in cache hit ratio over existing caching methods.

Effective algorithmic solutions with provable approximation guarantees.

Enhanced storage efficiency by sharing model parameters across multiple AI models.

Abstract

Next-generation mobile networks are expected to facilitate fast AI model downloading to end users. By caching models on edge servers, mobile networks can deliver models to end users with low latency, resulting in a paradigm called edge model caching. In this paper, we develop a novel model placement scheme, called parameter-sharing model caching (TrimCaching). TrimCaching exploits the key observation that a wide range of AI models, such as convolutional neural networks or large language models, can share a significant proportion of parameter blocks containing reusable knowledge, thereby improving storage efficiency. To this end, we formulate a parameter-sharing model placement problem to maximize the cache hit ratio in multi-edge wireless networks by balancing the fundamental tradeoff between storage efficiency and service latency. We show that the formulated problem is a submodular maximization problem with submodular constraints, for which no polynomial-time approximation algorithm exists. To overcome this challenge, we study an important special case, where a small fixed number of parameter blocks are shared across models, which often holds in practice. In such a case, a polynomial-time algorithm with $\left(1-\epsilon\right)/2$-approximation guarantee is developed. Subsequently, we address the original problem for the general case by developing a greedy algorithm. Simulation results demonstrate that the proposed TrimCaching framework significantly improves the cache hit ratio compared with state-of-the-art content caching without exploiting shared parameters in AI models.