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

• URL: http://arxiv.org/abs/2405.03990v2
• Date: Mon, 20 May 2024 03:44:52 GMT
• Title: TrimCaching: Parameter-sharing AI Model Caching in Wireless Edge Networks
• Authors: Guanqiao Qu, Zheng Lin, Fangming Liu, Xianhao Chen, Kaibin Huang,
• Abstract summary: 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. We develop a novel model placement scheme, called parameter-sharing model caching (TrimCaching)
• Score: 36.39118138582416
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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.

Related papers

• Resource-Efficient Generative AI Model Deployment in Mobile Edge Networks [15.958822667638405]
  The scarcity of available resources on the edge pose significant challenges in deploying generative AI models. We present a collaborative edge-cloud framework aiming to properly manage generative AI model deployment on the edge.
  arXiv  Detail & Related papers  (2024-09-09T03:17:28Z)
• Towards Robust and Efficient Cloud-Edge Elastic Model Adaptation via Selective Entropy Distillation [56.79064699832383]
  We establish a Cloud-Edge Elastic Model Adaptation (CEMA) paradigm in which the edge models only need to perform forward propagation. In our CEMA, to reduce the communication burden, we devise two criteria to exclude unnecessary samples from uploading to the cloud.
  arXiv  Detail & Related papers  (2024-02-27T08:47:19Z)
• On Optimal Caching and Model Multiplexing for Large Model Inference [66.50550915522551]
  Large Language Models (LLMs) and other large foundation models have achieved noteworthy success, but their size exacerbates existing resource consumption and latency challenges. We study two approaches for mitigating these challenges: employing a cache to store previous queries and learning a model multiplexer to choose from an ensemble of models for query processing.
  arXiv  Detail & Related papers  (2023-06-03T05:01:51Z)
• Multi-fidelity surrogate modeling using long short-term memory networks [0.0]
  We introduce a novel data-driven framework of multi-fidelity surrogate modeling for parametrized, time-dependent problems. We show that the proposed multi-fidelity LSTM networks not only improve single-fidelity regression significantly, but also outperform the multi-fidelity models based on feed-forward neural networks.
  arXiv  Detail & Related papers  (2022-08-05T12:05:02Z)
• Learning from Images: Proactive Caching with Parallel Convolutional Neural Networks [94.85780721466816]
  A novel framework for proactive caching is proposed in this paper. It combines model-based optimization with data-driven techniques by transforming an optimization problem into a grayscale image. Numerical results show that the proposed scheme can reduce 71.6% computation time with only 0.8% additional performance cost.
  arXiv  Detail & Related papers  (2021-08-15T21:32:47Z)
• Rate Distortion Characteristic Modeling for Neural Image Compression [59.25700168404325]
  End-to-end optimization capability offers neural image compression (NIC) superior lossy compression performance. distinct models are required to be trained to reach different points in the rate-distortion (R-D) space. We make efforts to formulate the essential mathematical functions to describe the R-D behavior of NIC using deep network and statistical modeling.
  arXiv  Detail & Related papers  (2021-06-24T12:23:05Z)
• Neural Closure Models for Dynamical Systems [35.000303827255024]
  We develop a novel methodology to learn non-Markovian closure parameterizations for low-fidelity models. New "neural closure models" augment low-fidelity models with neural delay differential equations (nDDEs) We show that using non-Markovian over Markovian closures improves long-term accuracy and requires smaller networks.
  arXiv  Detail & Related papers  (2020-12-27T05:55:33Z)
• Adaptive Subcarrier, Parameter, and Power Allocation for Partitioned Edge Learning Over Broadband Channels [69.18343801164741]
  partitioned edge learning (PARTEL) implements parameter-server training, a well known distributed learning method, in wireless network. We consider the case of deep neural network (DNN) models which can be trained using PARTEL by introducing some auxiliary variables.
  arXiv  Detail & Related papers  (2020-10-08T15:27:50Z)
• Artificial Intelligence Assisted Collaborative Edge Caching in Small Cell Networks [19.605382256630538]
  This paper considers heterogeneous content preference of the users with heterogeneous caching models at the edge nodes. We propose a modified particle swarm optimization (M-PSO) algorithm that efficiently solves the complex constraint problem in a reasonable time.
  arXiv  Detail & Related papers  (2020-05-16T10:39:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.