相关论文: ALDI++: Automatic and parameter-less discord and o…

In this letter, we propose an energy-efficient split learning (SL) framework for fine-tuning large language models (LLMs) using geo-distributed personal data at the network edge, where LLMs are split and alternately across massive mobile…

Anomaly detection is a prominent data preprocessing step in learning applications for correction and/or removal of faulty data. Automating this data type with the use of autoencoders could increase the quality of the dataset by isolating…

A well-performing prediction model is vital for a recommendation system suggesting actions for energy-efficient consumer behavior. However, reliable and accurate predictions depend on informative features and a suitable model design to…

Adversarial detection protects models from adversarial attacks by refusing suspicious test samples. However, current detection methods often suffer from weak generalization: their effectiveness tends to degrade significantly when applied to…

We study agnostic active learning, where the goal is to learn a classifier in a pre-specified hypothesis class interactively with as few label queries as possible, while making no assumptions on the true function generating the labels. The…

Deep neural networks (DNNs) are highly susceptible to adversarial samples, raising concerns about their reliability in safety-critical tasks. Currently, methods of evaluating adversarial robustness are primarily categorized into…

Discord is a refinement of the concept of anomalous subsequence of a time series. The task of discords discovery is applied in a wide range of subject domains related to time series: medicine, economics, climate modeling, etc. In this…

Machine learning systems increasingly drive innovation across scientific fields and industry, yet challenges in compute overhead, specifically during inference, limit their scalability and sustainability. Responsible AI guardrails,…

Learning at the edge is a challenging task from several perspectives, since data must be collected by end devices (e.g. sensors), possibly pre-processed (e.g. data compression), and finally processed remotely to output the result of…

Previous adversarial training raises model robustness under the compromise of accuracy on natural data. In this paper, we reduce natural accuracy degradation. We use the model logits from one clean model to guide learning of another one…

Energy disaggregation is the task of discerning the energy consumption of individual appliances from aggregated measurements, which holds promise for understanding and reducing energy usage. In this paper, we propose PHASED, an optimization…

Deep neural networks are vulnerable to adversarial examples. Adversarial training (AT) is an effective defense against adversarial examples. However, AT is prone to overfitting which degrades robustness substantially. Recently, data…

Deep learning models undergo a significant increase in the number of parameters they possess, leading to the execution of a larger number of operations during inference. This expansion significantly contributes to higher energy consumption…

We propose a computational method (with acronym ALDI) for sampling from a given target distribution based on first-order (overdamped) Langevin dynamics which satisfies the property of affine invariance. The central idea of ALDI is to run an…

Artificial intelligence (AI) - and specifically machine learning (ML) - applications for climate prediction across timescales are proliferating quickly. The emergence of these methods prompts a revisit to the impact of data preprocessing, a…

Designing neural network architectures is a challenging task and knowing which specific layers of a model must be adapted to improve the performance is almost a mystery. In this paper, we introduce a novel methodology to identify layers…

Accurately estimating workload runtime is a longstanding goal in computer systems, and plays a key role in efficient resource provisioning, latency minimization, and various other system management tasks. Runtime prediction is particularly…

Power and energy consumption is becoming key challenges to deploy the first exascale supercomputer successfully. Large-scale HPC applications waste a significant amount of power in communication and synchronization-related idle times.…

Parameter identification for mechanistic Ordinary Differential Equation (ODE) models underpins prediction and control in several applications, yet remains a manual and labor-intensive process: datasets are noisy and partial, models can be…

Domain adaptation in object detection is critical for real-world applications where distribution shifts degrade model performance. Security X-ray imaging presents a unique challenge due to variations in scanning devices and environmental…