Related papers: Remote Inference over Dynamic Links via Adaptive R…
Representation learning has overcome the often arduous and manual featurization of networks through (unsupervised) feature learning as it results in embeddings that can apply to a variety of downstream learning tasks. The focus of…
Embedding is a useful technique to project a high-dimensional feature into a low-dimensional space, and it has many successful applications including link prediction, node classification and natural language processing. Current approaches…
The application of the context-adaptive entropy model significantly improves the rate-distortion (R-D) performance, in which hyperpriors and autoregressive models are jointly utilized to effectively capture the spatial redundancy of the…
Deep learning-based semantic communication has largely relied on analog or semi-digital transmission, which limits compatibility with modern digital communication infrastructures. Recent studies have employed vector quantization (VQ) to…
Large Language Models (LLMs) typically rely on a large number of parameters for token embedding, leading to substantial storage requirements and memory footprints. In particular, LLMs deployed on edge devices are memory-bound, and reducing…
Performing unsupervised domain adaptation on resource-constrained edge devices is challenging. Existing research typically adopts architecture optimization (e.g., designing slimmable networks) but requires expensive training costs.…
Recent neural audio compression models often rely on residual vector quantization for high-fidelity coding, but using a fixed number of per-frame codebooks is suboptimal for the wide variability of audio content-especially for signals that…
Transformer models have been successful in various sequence processing tasks, but the self-attention mechanism's computational cost limits its practicality for long sequences. Although there are existing attention variants that improve…
Efficient lossless compression is essential for minimizing storage costs and transmission overhead while preserving data integrity. Traditional compression techniques, such as dictionary-based and statistical methods, often struggle to…
Contemporary deep learning, characterized by the training of cumbersome neural networks on massive datasets, confronts substantial computational hurdles. To alleviate heavy data storage burdens on limited hardware resources, numerous…
As the volume of image data grows, data-oriented cloud computing in Internet of Video Things (IoVT) systems encounters latency issues. Task-oriented edge computing addresses this by shifting data analysis to the edge. However, limited…
Data parallelism can boost the training speed of convolutional neural networks (CNN), but could suffer from significant communication costs caused by gradient aggregation. To alleviate this problem, several scalar quantization techniques…
Video compression plays a crucial role in video streaming and classification systems by maximizing the end-user quality of experience (QoE) at a given bandwidth budget. In this paper, we conduct the first systematic study for adversarial…
Flying ad hoc networks (FANETs) play a crucial role in numerous military and civil applications since it shortens mission duration and enhances coverage significantly compared with a single unmanned aerial vehicle (UAV). Whereas, designing…
As machine learning inferences increasingly move to edge devices, adapting to diverse computational capabilities, hardware, and memory constraints becomes more critical. Instead of relying on a pre-trained model fixed for all future…
Dynamic link prediction is important for modeling evolving interactions in complex systems, including social, communication, financial, and transportation networks. Classical temporal graph models capture sequential dependencies, but they…
Deep Neural Networks (DNNs) typically require massive amount of computation resource in inference tasks for computer vision applications. Quantization can significantly reduce DNN computation and storage by decreasing the bitwidth of…
Token-level adaptive computation seeks to reduce inference cost by allocating more computation to harder tokens and less to easier ones. However, prior work is primarily evaluated on natural-language benchmarks using task-level metrics,…
Learned image compression has exhibited promising compression performance, but variable bitrates over a wide range remain a challenge. State-of-the-art variable rate methods compromise the loss of model performance and require numerous…
Video large language models have demonstrated remarkable capabilities in video understanding tasks. However, the redundancy of video tokens introduces significant computational overhead during inference, limiting their practical deployment.…