5 papers
Robust Federated Learning Under Real-World Client Churn
Dhruv Garg, Neha Lakhani, Debopam Sanyal +3
Federated Learning (FL) enables training shared models on private, on-device data, but production deployments remain constrained to slow, multi-day refresh cycles due to the comple…
KLAS: Using Similarity to Stitch Neural Networks for Improved Accuracy-Efficiency Tradeoffs
Debopam Sanyal, Anantharaman Iyer, Alind Khare +5
Given the wide range of deployment targets, flexible model selection is essential for optimizing performance within a given compute budget. Recent work demonstrates that stitching…
DεpS: Delayed ε-Shrinking for Faster Once-For-All Training
Aditya Annavajjala, Alind Khare, Animesh Agrawal +4
CNNs are increasingly deployed across different hardware, dynamic environments, and low-power embedded devices. This has led to the design and training of CNN architectures with th…
SuperServe: Fine-Grained Inference Serving for Unpredictable Workloads
Alind Khare, Dhruv Garg, Sukrit Kalra +3
The increasing deployment of ML models on the critical path of production applications in both datacenter and the edge requires ML inference serving systems to serve these models u…
STRIDE: Structure and Embedding Distillation with Attention for Graph Neural Networks
Anshul Ahluwalia, Payman Behnam, Rohit Das +4
Recent advancements in Graph Neural Networks (GNNs) have led to increased model sizes to enhance their capacity and accuracy. Such large models incur high memory usage, latency, an…