1

Circa reduces the runtime overhead of ReLU operation by 1.9x by decoupling the sign evaluation and multiplication steps in the Garbled circuit with no loss in accuracy. Further, it achieves a total of 4.7x runtime reduction by employing the sign approximation in the Garbled circuit by leveraging the error-tolerant properties of neural networks within a 1% accuracy margin.

DeepReDuce is a set of optimizations for the judicious removal of ReLUs to reduce private inference latency by leveraging the ReLUs heterogeneity in classical networks. DeepReDuce strategically drops ReLUs upto 4.9x (on CIFAR-100) and 5.7x (on TinyImageNet) for ResNet18 with no loss in accuracy. Compared to the state-of-the-art for private inference DeepReDuce improves accuracy and reduces ReLU count by up to 3.5% (iso-ReLU) and 3.5×(iso-accuracy), respectively.

In this work, we address the low PE utilization and low data reuse challenges in the memory-bound DNNs stem either from depthwise convolution or the very less number of channels in each group. We proposed DNN-optimization techniques that strike a balance between PE utilization, energy efficiency, and accuracy of the DNNs.

The capability of the self-attention mechanism to model the long-range dependencies has catapulted its deployment in vision models. …

The number of groups (g) in group convolution (GConv) is selected to boost the predictive performance of deep neural networks (DNNs) in …

The recent trend in deep neural networks (DNNs) research is to make the networks more compact. The motivation behind designing compact …

In two-party machine learning prediction services, the client’s goal is to query a remote server’s trained machine learning …

DeepReShape is the first work to conduct a rigorous characterization of desirable neural network attributes for efficient Private Inference (PI). We discovered that distinct network attributes are required for different ReLU counts; in particular, wider networks are beneficial only for higher ReLU counts, whereas networks with a greater proportion of least-critical ReLU are desirable for lower ReLU counts. Further, we introduced a novel network design principle called “ReLU-equalization” to strategically allocate channels within the network to optimize ReLUs and FLOPs efficiency simultaneously. DeepReShape outperforms the current SOTA (SENets, ICLR'23) by achieving a 2.1% increase in accuracy and a 5.2x faster runtime at iso-ReLU counts on CIFAR-100, and an 8.7x faster runtime at iso-accuracy on the TinyImageNet dataset.