Search Results for author:
Found 16 papers, 7 papers with code
Privacy-Preserving Training-as-a-Service for On-Device Intelligence: Concept, Architectural Scheme, and Open Problems
On-device intelligence (ODI) enables artificial intelligence (AI) applications to run on end devices, providing real-time and customized AI services without relying on remote servers.
LIX: Implicitly Infusing Spatial Geometric Prior Knowledge into Visual Semantic Segmentation for Autonomous Driving
We introduce the Learning to Infuse "X" (LIX) framework, with novel contributions in both logit distillation and feature distillation aspects.
S$^3$M-Net: Joint Learning of Semantic Segmentation and Stereo Matching for Autonomous Driving
Hence, in this article, we introduce S$^3$M-Net, a novel joint learning framework developed to perform semantic segmentation and stereo matching simultaneously.
Logits Poisoning Attack in Federated Distillation
Federated Distillation (FD) is a novel and promising distributed machine learning paradigm, where knowledge distillation is leveraged to facilitate a more efficient and flexible cross-device knowledge transfer in federated learning.
Federated Class-Incremental Learning with New-Class Augmented Self-Distillation
Federated Learning (FL) enables collaborative model training among participants while guaranteeing the privacy of raw data.
Improving Communication Efficiency of Federated Distillation via Accumulating Local Updates
ALU drastically decreases the frequency of communication in federated distillation, thereby significantly reducing the communication overhead during the training process.
Agglomerative Federated Learning: Empowering Larger Model Training via End-Edge-Cloud Collaboration
Federated Learning (FL) enables training Artificial Intelligence (AI) models over end devices without compromising their privacy.
Federated Skewed Label Learning with Logits Fusion
By fusing the logits of the two models, the private weak learner can capture the variance of different data, regardless of their category.
Knowledge Distillation in Federated Edge Learning: A Survey
The increasing demand for intelligent services and privacy protection of mobile and Internet of Things (IoT) devices motivates the wide application of Federated Edge Learning (FEL), in which devices collaboratively train on-device Machine Learning (ML) models without sharing their private data.
FedICT: Federated Multi-task Distillation for Multi-access Edge Computing
Federated Multi-task Learning (FMTL) is proposed to train related but personalized ML models for different devices, whereas previous works suffer from excessive communication overhead during training and neglect the model heterogeneity among devices in MEC.
Semi-supervised Training for Knowledge Base Graph Self-attention Networks on Link Prediction
The task of link prediction aims to solve the problem of incomplete knowledge caused by the difficulty of collecting facts from the real world.
Exploring the Distributed Knowledge Congruence in Proxy-data-free Federated Distillation
Federated distillation (FD) is proposed to simultaneously address the above two problems, which exchanges knowledge between the server and clients, supporting heterogeneous local models while significantly reducing communication overhead.
Meta-Learning-Based Deep Reinforcement Learning for Multiobjective Optimization Problems
When these problems are extended to multiobjective ones, it becomes difficult for the existing DRL approaches to flexibly and efficiently deal with multiple subproblems determined by weight decomposition of objectives.
Spirit Distillation: A Model Compression Method with Multi-domain Knowledge Transfer
To further improve the robustness of the student, we extend SD to Enhanced Spirit Distillation (ESD) in exploiting a more comprehensive knowledge by introducing the proximity domain which is similar to the target domain for feature extraction.
Spirit Distillation: Precise Real-time Semantic Segmentation of Road Scenes with Insufficient Data
Inspired by the ideas of Fine-tuning-based Transfer Learning (FTT) and feature-based knowledge distillation, we propose a new knowledge distillation method for cross-domain knowledge transference and efficient data-insufficient network training, named Spirit Distillation(SD), which allow the student network to mimic the teacher network to extract general features, so that a compact and accurate student network can be trained for real-time semantic segmentation of road scenes.
Activation Map Adaptation for Effective Knowledge Distillation
Model compression becomes a recent trend due to the requirement of deploying neural networks on embedded and mobile devices.
