相关论文: MERGE: Fast Private Text Generation

An unsolved challenge in distributed or federated learning is to effectively mitigate privacy risks without slowing down training or reducing accuracy. In this paper, we propose TextHide aiming at addressing this challenge for natural…

With the increasing demands for privacy protection, many privacy-preserving machine learning systems were proposed in recent years. However, most of them cannot be put into production due to their slow training and inference speed caused by…

Deep neural networks are increasingly being used in a variety of machine learning applications applied to rich user data on the cloud. However, this approach introduces a number of privacy and efficiency challenges, as the cloud operator…

Ensuring the privacy of users whose data are used to train Natural Language Processing (NLP) models is necessary to build and maintain customer trust. Differential Privacy (DP) has emerged as the most successful method to protect the…

Large-scale transformers are central to modern semantic communication, yet their high computational and communication costs hinder deployment on resource-constrained edge devices. This paper introduces a training-free framework for adaptive…

Large Language Models (LLMs) excel at a wide range of tasks, but adapting them to new data, particularly for personalized applications, poses significant challenges due to resource and computational constraints. Existing methods either rely…

Large Language Models (LLMs) have demonstrated impressive performance across various tasks, with different models excelling in distinct domains and specific abilities. Effectively combining the predictions of multiple LLMs is crucial for…

In collaborative software development, program merging is the mechanism to integrate changes from multiple programmers. Merge algorithms in modern version control systems report a conflict when changes interfere textually. Merge conflicts…

Transformer-based text embedding models have improved their performance on benchmarks like MIRACL and BEIR by increasing their parameter counts. However, this scaling approach introduces significant deployment challenges, including…

In recent years, large language models have demonstrated remarkable performance across various natural language processing (NLP) tasks. However, deploying these models for real-world applications often requires efficient inference solutions…

Although masked language models are highly performant and widely adopted by NLP practitioners, they can not be easily used for autoregressive language modelling (next word prediction and sequence probability estimation). We present an…

Adapting general-purpose language models to new skills is currently an expensive process that must be repeated as new instruction datasets targeting new skills are created, or can cause the models to forget older skills. In this work, we…

Non-autoregressive (NAR) text generation has attracted much attention in the field of natural language processing, which greatly reduces the inference latency but has to sacrifice the generation accuracy. Recently, diffusion models, a class…

Incorporating fully homomorphic encryption (FHE) into the inference process of a convolutional neural network (CNN) draws enormous attention as a viable approach for achieving private inference (PI). FHE allows delegating the entire…

Existing approaches in Federated Learning (FL) mainly focus on sending model parameters or gradients from clients to a server. However, these methods are plagued by significant inefficiency, privacy, and security concerns. Thanks to the…

Large Language Models are growing in size, and we expect them to continue to do so, as larger models train quicker. However, this increase in size will severely impact inference costs. Therefore model compression is important, to retain the…

Model merging constructs versatile models by integrating task-specific models without requiring labeled data or expensive joint retraining. Although recent methods improve adaptability to heterogeneous tasks by generating customized merged…

Recent large-scale natural language processing (NLP) systems use a pre-trained Large Language Model (LLM) on massive and diverse corpora as a headstart. In practice, the pre-trained model is adapted to a wide array of tasks via fine-tuning…

The success of large language models (LLMs) facilitate many parties to fine-tune LLMs on their own private data. However, this practice raises privacy concerns due to the memorization of LLMs. Existing solutions, such as utilizing synthetic…

With the growing adoption of privacy-preserving machine learning algorithms, such as Differentially Private Stochastic Gradient Descent (DP-SGD), training or fine-tuning models on private datasets has become increasingly prevalent. This…