相关论文: Lightweight User-Personalization Method for Closed…

Split learning (SL) enables collaborative training by partitioning a neural network across clients and a central server, but the cut-layer interface introduces a key challenge: high-dimensional activations incur substantial communication…

Recent advances in deep learning have significantly improved predictive accuracy. However, modern neural networks remain systematically overconfident, posing risks for deployment in safety-critical scenarios. Current post-hoc calibration…

With the prevalence of Large Learning Models (LLM), Split Federated Learning (SFL), which divides a learning model into server-side and client-side models, has emerged as an appealing technology to deal with the heavy computational burden…

The field of autonomous driving technology is rapidly advancing, with deep learning being a key component. Particularly in the field of sensing, 3D point cloud data collected by LiDAR is utilized to run deep neural network models for 3D…

In this paper, we propose a novel approach to minimize the inference delay in semantic segmentation using split learning (SL), tailored to the needs of real-time computer vision (CV) applications for resource-constrained devices. Semantic…

Recently collaborative learning is widely applied to model sensitive data generated in Industrial IoT (IIoT). It enables a large number of devices to collectively train a global model by collaborating with a server while keeping the…

Federated learning (FL) enables collaborative model training across distributed clients (e.g., edge devices) without sharing raw data. Yet, FL can be computationally expensive as the clients need to train the entire model multiple times.…

Speaker anonymization aims to conceal a speaker's identity without degrading speech quality and intelligibility. Most speaker anonymization systems disentangle the speaker representation from the original speech and achieve anonymization by…

Split computing has emerged as a recent paradigm for implementation of DNN-based AI workloads, wherein a DNN model is split into two parts, one of which is executed on a mobile/client device and the other on an edge-server (or cloud). Data…

Multimodal transformers integrate diverse data types like images, audio, and text, advancing tasks such as audio-visual understanding and image-text retrieval; yet their high parameterization limits deployment on resource-constrained edge…

We present a novel method, SALAD, for the challenging vision task of adapting a pre-trained "source" domain network to a "target" domain, with a small budget for annotation in the "target" domain and a shift in the label space. Further, the…

The rapid scaling of large vision pretrained models makes fine-tuning tasks more and more difficult on devices with low computational resources. We explore a new visual adaptation paradigm called separated tuning, which treats large…

Split learning (SL) addresses the limitation of running deep learning inference directly on low-power edge/IoT nodes, in which it executes part of the inference process on the sensor and offloading the remainder to a companion device.…

Large language models exhibit strong reasoning capabilities, yet often rely on shortcuts such as surface pattern matching and answer memorization rather than genuine logical inference. We propose Shortcut-Aware Reasoning Training (SART), a…

Large pre-trained models have exhibited remarkable achievements across various domains. The substantial training costs associated with these models have led to wide studies of fine-tuning for effectively harnessing their capabilities in…

Split learning (SL) transfers most of the training workload to the server, which alleviates computational burden on client devices. However, the transmission of intermediate feature representations, referred to as smashed data, incurs…

There has been growing interest in parameter-efficient methods to apply pre-trained language models to downstream tasks. Building on the Prompt Tuning approach of Lester et al. (2021), which learns task-specific soft prompts to condition a…

Imbalanced datasets pose a considerable challenge in training deep learning (DL) models for medical diagnostics, particularly for segmentation tasks. Imbalance may be associated with annotation quality limited annotated datasets, rare…

Federated learning (FL) emerged as a popular distributed algorithm to train machine learning models on edge devices while preserving data privacy. However, FL systems face challenges due to client-side computational constraints and from a…

Transfer learning has become a popular task adaptation method in the era of foundation models. However, many foundation models require large storage and computing resources, which makes off-the-shelf deployment impractical. Post-training…