Related papers: Phaedrus: Predicting Dynamic Application Behavior …

Conventional feature selection algorithms applied to Pseudo Time-Series (PTS) data, which consists of observations arranged in sequential order without adhering to a conventional temporal dimension, often exhibit impractical computational…

Specializing an OS to optimize the performance of a particular application is typically a manual process that requires great expertise. Specialization through configuration lends itself well to automation; however, it is challenging due to…

Nowadays, software artifacts are ubiquitous in our lives being an essential part of home appliances, cars, cell phones, and even in more critical activities like aeronautics and health sciences. In this context software failures may produce…

Existing works show that augmenting the training data of pre-trained language models (PLMs) for classification tasks fine-tuned via parameter-efficient fine-tuning methods (PEFT) using both clean and adversarial examples can enhance their…

Software fault prediction (SFP) is a critical task in software engineering, enabling early identification of faults in modules to improve software quality and reduce maintenance costs. This research investigates the combined effects of…

This paper presents a novel methodology of fine-tuning for large language models-dynamic LoRA. Building from the standard Low-Rank Adaptation framework, this methodology further adds dynamic adaptation mechanisms to improve efficiency and…

Memory Dependence Prediction (MDP) is a speculative technique to determine which stores, if any, a given load will depend on. Area-constrained cores are increasingly relevant in various applications such as energy-efficient or edge systems,…

Traditionally, machine learning methods for PE malware detection have relied on static features like byte histograms, string information, and PE header contents. One barrier to incorporating dynamic analysis features has been the…

Beyond scaling base models with more data or parameters, fine-tuned adapters provide an alternative way to generate high fidelity, custom images at reduced costs. As such, adapters have been widely adopted by open-source communities,…

Modern software systems are increasingly designed to be highly configurable, which increases flexibility but can make programs harder to develop, test, and analyze, e.g., how configuration options are set to reach certain locations, what…

Despite achieving remarkable performance, Federated Learning (FL) encounters two important problems, i.e., low training efficiency and limited computational resources. In this paper, we propose a new FL framework, i.e., FedDUMAP, with three…

Extreme-scale scientific applications can be more vulnerable to soft errors (transient faults) as high-performance computing systems increase in scale. The common practice to evaluate the resilience to faults of an application is random…

Federated Learning (FL) enables collaborative model training across distributed clients without data sharing, but its high computational and communication demands strain resource-constrained devices. While existing methods use dynamic…

When faced with changing environment, highly configurable software systems need to dynamically search for promising adaptation plan that keeps the best possible performance, e.g., higher throughput or smaller latency -- a typical planning…

Energy consumption plays a vital role in mobile App development for developers and end-users, and it is considered one of the most crucial factors for purchasing a smartphone. In addition, in terms of sustainability, it is essential to find…

Parameter-efficient fine-tuning (PEFT) allows model builders to capture the task-specific parameters into adapters, which are a fraction of the size of the original base model. Popularity of PEFT technique for fine-tuning has led to the…

Adapting large pretrained models to diverse tasks is now routine, yet the two dominant strategies of parameter-efficient fine-tuning (PEFT) and low-rank compression are typically composed in sequence. This decoupled practice first…

Faster inference of deep learning models is highly demanded on edge devices and even servers, for both financial and environmental reasons. To address this issue, we propose SoftNeuro, a novel, high-performance inference framework with…

This survey delves into the realm of Parameter-Efficient Fine-Tuning (PEFT) within the context of Foundation Models (FMs). PEFT, a cost-effective fine-tuning technique, minimizes parameters and computational complexity while striving for…

Fine-tuning all parameters of Large Language Models (LLMs) is computationally expensive. Parameter-Efficient Fine-Tuning (PEFT) methods address this by selectively fine-tuning specific parameters. Most of the parameter efficient fine-tuning…