Related papers: Memory Constrained Dynamic Subnetwork Update for T…

The limited and dynamically varied resources on edge devices motivate us to deploy an optimized deep neural network that can adapt its sub-networks to fit in different resource constraints. However, existing works often build sub-networks…

Timely delivery of delay-sensitive information over dynamic, heterogeneous networks is increasingly essential for a range of interactive applications, such as industrial automation, self-driving vehicles, and augmented reality. However,…

Unsupervised machine translation, which utilizes unpaired monolingual corpora as training data, has achieved comparable performance against supervised machine translation. However, it still suffers from data-scarce domains. To address this…

Sampling from discrete distributions with multiple modes and energy barriers is fundamental to machine learning and computational physics. Recent discrete neural samplers like MDNS suffer from mode collapse and fail to sample high-energy…

Deep learning is reshaping mobile applications, with a growing trend of deploying deep neural networks (DNNs) directly to mobile and embedded devices to address real-time performance and privacy. To accommodate local resource limitations,…

In this paper, we build upon the weakly-supervised generation mechanism of intermediate attention maps in any convolutional neural networks and disclose the effectiveness of attention modules more straightforwardly to fully exploit their…

Deep neural networks can yield good performance on various tasks but often require large amounts of data to train them. Meta-learning received considerable attention as one approach to improve the generalization of these networks from a…

The anticipated increase in the count of IoT devices in the coming years motivates the development of efficient algorithms that can help in their effective management while keeping the power consumption low. In this paper, we propose an…

Linear Attention (LA) offers a promising paradigm for scaling large language models (LLMs) to long sequences by avoiding the quadratic complexity of self-attention. Recent LA models such as Mamba2 and GDN interpret linear recurrences as…

Using neural networks in practical settings would benefit from the ability of the networks to learn new tasks throughout their lifetimes without forgetting the previous tasks. This ability is limited in the current deep neural networks by a…

How to adapt a pre-trained model continuously for sequential tasks with different prediction class labels and domains and finally learn a generalizable model across diverse tasks is a long-lasting challenge. Continual learning (CL) has…

Domain adaptation (DA) enables knowledge transfer from a labeled source domain to an unlabeled target domain by reducing the cross-domain distribution discrepancy. Most prior DA approaches leverage complicated and powerful deep neural…

Resource-efficient convolution neural networks enable not only the intelligence on edge devices but also opportunities in system-level optimization such as scheduling. In this work, we aim to improve the performance of resource-constrained…

Learning an efficient update rule from data that promotes rapid learning of new tasks from the same distribution remains an open problem in meta-learning. Typically, previous works have approached this issue either by attempting to train a…

Neural networks have achieved tremendous success in a large variety of applications. However, their memory footprint and computational demand can render them impractical in application settings with limited hardware or energy resources. In…

Recognizing new objects by learning from a few labeled examples in an evolving environment is crucial to obtain excellent generalization ability for real-world machine learning systems. A typical setting across current meta learning…

Next-generation networks aim to provide performance guarantees to real-time interactive services that require timely and cost-efficient packet delivery. In this context, the goal is to reliably deliver packets with strict deadlines imposed…

Network slicing is a promising technology that allows mobile network operators to efficiently serve various emerging use cases in 5G. It is challenging to optimize the utilization of network infrastructures while guaranteeing the…

In deep Reinforcement Learning (RL), the learning rate critically influences both stability and performance, yet its optimal value shifts during training as the environment and policy evolve. Standard decay schedulers assume monotonic…

Incremental learning aims to adapt to new sets of categories over time with minimal computational overhead. Prior work often addresses this task by training efficient task-specific adaptors that modify frozen layer weights or features to…