5 papers · 1 filter
DriftGuard: Mitigating Asynchronous Data Drift in Federated Learning
Yizhou Han, Di Wu, Blesson Varghese
In real-world Federated Learning (FL) deployments, data distributions on devices that participate in training evolve over time. This leads to asynchronous data drift, where differe…
Data-Free Pruning of Self-Attention Layers in LLMs
Dhananjay Saikumar, Blesson Varghese
Many self-attention sublayers in large language models (LLMs) can be removed with little to no loss. We attribute this to the Attention Suppression Hypothesis: during pre-training,…
Mosaic: Composite Projection Pruning for Resource-efficient LLMs
Bailey J. Eccles, Leon Wong, Blesson Varghese
Extensive compute and memory requirements limit the deployment of large language models (LLMs) on any hardware. Compression methods, such as pruning, can reduce model size, which i…
Signal Collapse in One-Shot Pruning: When Sparse Models Fail to Distinguish Neural Representations
Dhananjay Saikumar, Blesson Varghese
Neural network pruning is essential for reducing model complexity to enable deployment on resource constrained hardware. While performance loss of pruned networks is often attribut…
Rapid Deployment of DNNs for Edge Computing via Structured Pruning at Initialization
Bailey J. Eccles, Leon Wong, Blesson Varghese
Edge machine learning (ML) enables localized processing of data on devices and is underpinned by deep neural networks (DNNs). However, DNNs cannot be easily run on devices due to t…