Search Results for author:
Found 12 papers, 7 papers with code
AdaGossip: Adaptive Consensus Step-size for Decentralized Deep Learning with Communication Compression
Decentralized learning is crucial in supporting on-device learning over large distributed datasets, eliminating the need for a central server.
Towards Two-Stream Foveation-based Active Vision Learning
Specifically, the proposed framework models the following mechanisms: 1) ventral (what) stream focusing on the input regions perceived by the fovea part of an eye (foveation), 2) dorsal (where) stream providing visual guidance, and 3) iterative processing of the two streams to calibrate visual focus and process the sequence of focused image patches.
Averaging Rate Scheduler for Decentralized Learning on Heterogeneous Data
State-of-the-art decentralized learning algorithms typically require the data distribution to be Independent and Identically Distributed (IID).
Cross-feature Contrastive Loss for Decentralized Deep Learning on Heterogeneous Data
The current state-of-the-art decentralized learning algorithms mostly assume the data distribution to be Independent and Identically Distributed (IID).
Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data
Decentralized learning enables the training of deep learning models over large distributed datasets generated at different locations, without the need for a central server.
Homogenizing Non-IID datasets via In-Distribution Knowledge Distillation for Decentralized Learning
The goal of IDKD is to homogenize the data distribution across the nodes.
CoDeC: Communication-Efficient Decentralized Continual Learning
Decentralized learning allows serverless training with spatially distributed data.
Neighborhood Gradient Clustering: An Efficient Decentralized Learning Method for Non-IID Data Distributions
Our experiments demonstrate that \textit{NGC} and \textit{CompNGC} outperform (by $0-6\%$) the existing SoTA decentralized learning algorithm over non-IID data with significantly less compute and memory requirements.
Low Precision Decentralized Distributed Training over IID and non-IID Data
In this paper, we propose and show the convergence of low precision decentralized training that aims to reduce the computational complexity and communication cost of decentralized training.
Sparse-Push: Communication- & Energy-Efficient Decentralized Distributed Learning over Directed & Time-Varying Graphs with non-IID Datasets
Current deep learning (DL) systems rely on a centralized computing paradigm which limits the amount of available training data, increases system latency, and adds privacy and security constraints.
Relevant-features based Auxiliary Cells for Energy Efficient Detection of Natural Errors
To address this issue, we propose an ensemble of classifiers at hidden layers to enable energy efficient detection of natural errors.
Gradual Channel Pruning while Training using Feature Relevance Scores for Convolutional Neural Networks
To address all the above issues, we present a simple-yet-effective gradual channel pruning while training methodology using a novel data-driven metric referred to as feature relevance score.
