Search Results - Computing methodologies Machine learning Learning paradigms Multi-task learning

CAE-DFKD: Bridging the Transferability Gap in Data-Free Knowledge Distillation by Zhang, Zherui, Wang, Changwei, Xu, Rongtao, Xu, Wenhao, Xu, Shibiao, Zhang, Yu, Zhou, Jie, Guo, Li

“… The superiority and flexibility of CAE-DFKD are extensively evaluated, including: i.) Significant efficiency advantages resulting from altering the generator training paradigm…”
Get full text

IFHE: Intermediate-Feature Heterogeneity Enhancement for Image Synthesis in Data-Free Knowledge Distillation by Chen, Yi, Liu, Ning, Ren, Ao, Yang, Tao, Liu, Duo

“…Data-free knowledge distillation (DFKD) explores training a compact student network only by a pre-trained teacher without real data. Prevailing DFKD methods…”
Get full text

Enabling On-Device Self-Supervised Contrastive Learning with Selective Data Contrast by Wu, Yawen, Wang, Zhepeng, Zeng, Dewen, Shi, Yiyu, Hu, Jingtong

“… Contrastive learning has demonstrated its great potential in learning from unlabeled data. However, the online input data are usually none independent and identically distributed (non-iid…”
Get full text

Muffin: A Framework Toward Multi-Dimension AI Fairness by Uniting Off-the-Shelf Models by Sheng, Yi, Yang, Junhuan, Yang, Lei, Shi, Yiyu, Hu, Jingtong, Jiang, Weiwen

“…Model fairness (a.k.a., bias) has become one of the most critical problems in a wide range of AI applications. An unfair model in autonomous driving may cause…”
Get full text

LA-MTL: Latency-Aware Automated Multi-Task Learning by Sampath, Shambhavi Balamuthu, Sawani, Sami, Thoma, Moritz, Frickenstein, Lukas, Mori, Pierpaolo, Fasfous, Nael, Vemparala, Manoj Rohit, Frickenstein, Alexander, Schlichtmann, Ulf, Passerone, Claudio, Stechele, Walter

“…Multi-Task Learning (MTL) aims to unify a variety of tasks into a single network for improved training and inference efficiency…”
Get full text

DistHD: A Learner-Aware Dynamic Encoding Method for Hyperdimensional Classification by Wang, Junyao, Huang, Sitao, Imani, Mohsen

“… Many applications exploit machine learning methodology to dissect collected data, and edge computing was introduced to enhance the efficiency and scalability in resource-constrained computing environments…”
Get full text

AppealNet: An Efficient and Highly-Accurate Edge/Cloud Collaborative Architecture for DNN Inference by Li, Min, Li, Yu, Tian, Ye, Jiang, Li, Xu, Qiang

“…This paper presents AppealNet, a novel edge/cloud collaborative architecture that runs deep learning (DL…”
Get full text

Shoggoth: Towards Efficient Edge-Cloud Collaborative Real-Time Video Inference via Adaptive Online Learning by Wang, Liang, Lu, Kai, Zhang, Nan, Qu, Xiaoyang, Wang, Jianzong, Wan, Jiguang, Li, Guokuan, Xiao, Jing

“… At the edge, we design adaptive training using small batches to adapt models under limited computing power, and adaptive sampling of training frames for robustness and reducing bandwidth…”
Get full text

MMDFL: Multi-Model-based Decentralized Federated Learning for Resource-Constrained AIoT Systems by Yan, Dengke, Yang, Yanxin, Hu, Ming, Fu, Xin, Chen, Mingsong

“…) applications adopt Federated Learning (FL) to enable collaborative learning without compromising the privacy of devices…”
Get full text

Dissecting Global Search: A Simple Yet Effective Method to Boost Individual Discrimination Testing and Repair by Quan, Lili, Li, Tianlin, Xie, Xiaofei, Chen, Zhenpeng, Chen, Sen, Jiang, Lingxiao, Li, Xiaohong

“…Deep Learning (DL) has achieved significant success in socially critical decision-making applications but often exhibits unfair behaviors, raising social concerns…”
Get full text

On-the-fly Improving Performance of Deep Code Models via Input Denoising by Tian, Zhao, Chen, Junjie, Zhang, Xiangyu

“…Deep learning has been widely adopted to tackle various code-based tasks by building deep code models based on a large amount of code snippets…”
Get full text

Robust Tickets Can Transfer Better: Drawing More Transferable Subnetworks in Transfer Learning by Fu, Yonggan, Yuan, Ye, Wu, Shang, Yuan, Jiayi, Lin, Yingyan Celine

“…Transfer learning leverages feature representations of deep neural networks (DNNs) pretrained on source tasks with rich data to empower effective finetuning on downstream tasks…”
Get full text

CascadeHD: Efficient Many-Class Learning Framework Using Hyperdimensional Computing by Kim, Yeseong, Kim, Jiseung, Imani, Mohsen

“…The brain-inspired hyperdimensional computing (HDC) gains attention as a light-weight and extremely parallelizable learning solution alternative to deep neural networks…”
Get full text

Self-Supervised Representation Learning and Temporal-Spectral Feature Fusion for Bed Occupancy Detection by Song, Yingjian, Pitafi, Zaid Farooq, Dou, Fei, Sun, Jin, Zhang, Xiang, Phillips, Bradley G, Song, Wenzhan

“… This paper introduces SeismoDot, which consists of a self-supervised learning module and a spectral-temporal feature fusion module for bed occupancy detection…”
Get more information

NetBooster: Empowering Tiny Deep Learning By Standing on the Shoulders of Deep Giants by Yu, Zhongzhi, Fu, Yonggan, Yuan, Jiayi, You, Haoran, Lin, Yingyan Celine

“…Tiny deep learning has attracted increasing attention driven by the substantial demand for deploying deep learning on numerous intelligent Internet-of-Things devices…”
Get full text

Condense: A Framework for Device and Frequency Adaptive Neural Network Models on the Edge by Gong, Yifan, Zhao, Pu, Zhan, Zheng, Wu, Yushu, Wu, Chao, Kong, Zhenglun, Qin, Minghai, Ding, Caiwen, Wang, Yanzhi

“…With the popularity of battery-powered edge computing, an important yet under-explored problem is the supporting of DNNs for diverse edge devices…”
Get full text

Lightning Talk: Bridging Neuro-Dynamics and Cognition by Imani, Mohsen

“…Brain-inspired computing models have shown great potential to outperform today's deep learning solutions in terms of robustness and energy efficiency…”
Get full text

Lightning Talk 6: Bringing Together Foundation Models and Edge Devices by Eliopoulos, Nick John, Lu, Yung-Hsiang

“… Existing methods to improve efficiency often require new architectures and retraining. The recent trend in machine learning is to create general-purpose models…”
Get full text

A Unified DNN Weight Pruning Framework Using Reweighted Optimization Methods by Zhang, Tianyun, Ma, Xiaolong, Zhan, Zheng, Zhou, Shanglin, Ding, Caiwen, Fardad, Makan, Wang, Yanzhi

“…To address the large model size and intensive computation requirement of deep neural networks (DNNs), weight pruning techniques have been proposed and…”
Get full text

Enabling On-Tiny-Device Model Personalization via Gradient Condensing and Alternant Partial Update by Jia, Zhenge, Shi, Yiyang, Bao, Zeyu, Wang, Zirui, Pang, Xin, Liu, Huiguo, Duan, Yu, Shen, Zhaoyan, Zhao, Mengying

“…On-device training enables the model to adapt to user-specific data by fine-tuning a pre-trained model locally. As embedded devices become ubiquitous,…”
Get full text