Combining Cloud and Mobile Computing for Machine Learning

Although the computing power of mobile devices is increasing, machine learning models are also growing in size. This trend creates problems for mobile devices due to limitations like their memory capacity and battery life. While many services, like ChatGPT and Midjourney, run all the inferences in the cloud, we believe a flexible and fine-grained task distribution is more desirable. In this work, we consider model segmentation as a solution to improving the user experience, dividing the computation between mobile devices and the cloud in a way that offloads the compute-heavy portion of the model while minimizing the data transfer required. We show that the division not only reduces the wait time for users but can also be fine-tuned to optimize the workloads of the cloud. To achieve that, we design a scheduler that collects information about network quality, client device capability, and job requirements, making decisions to achieve consistent performance across a range of devices while reducing the work the cloud needs to perform.

Specializing Small Language Models towards Complex Style Transfer via Latent Attribute Pre-Training

In this work, we introduce the concept of complex text style transfer tasks, and constructed complex text datasets based on two widely applicable scenarios. Our dataset is the first large-scale data set of its kind, with 700 rephrased sentences and 1,000 sentences from the game Genshin Impact. While large language models (LLM) have shown promise in complex text style transfer, they have drawbacks such as data privacy concerns, network instability, and high deployment costs. To address these issues, we explore the effectiveness of small models (less than T5-3B) with implicit style pre-training through contrastive learning. We also propose a method for automated evaluation of text generation quality based on alignment with human evaluations using ChatGPT. Finally, we compare our approach with existing methods and show that our model achieves state-of-art performances of few-shot text style transfer models.

Non-Transferable Learning: A New Approach for Model Verification and Authorization

As Artificial Intelligence as a Service gains popularity, protecting well-trained models as intellectual property is becoming increasingly important. Generally speaking, there are two common protection methods: ownership verification and usage authorization. In this paper, we propose Non-Transferable Learning (NTL), a novel approach that captures the exclusive data representation in the learned model and restricts the model generalization ability to certain domains. This approach provides effective solutions to both model verification and authorization. For ownership verification, watermarking techniques are commonly used but are often vulnerable to sophisticated watermark removal methods. Our NTL-based model verification approach instead provides robust resistance to state-of-the-art watermark removal methods, as shown in extensive experiments for four of such methods over the digits, CIFAR10 & STL10, and VisDA datasets. For usage authorization, prior solutions focus on authorizing specific users to use the model, but authorized users can still apply the model to any data without restriction. Our NTL-based authorization approach instead provides data-centric usage protection by significantly degrading the performance of usage on unauthorized data. Its effectiveness is also shown through experiments on a variety of datasets.