Deep neural networks (DNNs) underpin many machine learning applications. Production quality DNN models achieve high inference accuracy by training millions of DNN parameters which has a significant resource footprint. This presents a challenge for resources operating at the extreme edge of the network, such as mobile and embedded devices that have limited computational and memory resources. To address this, models are pruned to create lightweight, more suitable variants for these devices. Existing pruning methods are unable to provide similar quality models compared to their unpruned counterparts without significant time costs and overheads or are limited to offline use cases. Our work rapidly derives suitable model variants while maintaining the accuracy of the original model. The model variants can be swapped quickly when system and network conditions change to match workload demand. This paper presents DNNShifter , an end-to-end DNN training, spatial pruning, and model switching system that addresses the challenges mentioned above. At the heart of DNNShifter is a novel methodology that prunes sparse models using structured pruning - combining the accuracy-preserving benefits of unstructured pruning with runtime performance improvements of structured pruning. The pruned model variants generated by DNNShifter are smaller in size and thus faster than dense and sparse model predecessors, making them suitable for inference at the edge while retaining near similar accuracy as of the original dense model. DNNShifter generates a portfolio of model variants that can be swiftly interchanged depending on operational conditions. DNNShifter produces pruned model variants up to 93x faster than conventional training methods. Compared to sparse models, the pruned model variants are up to 5.14x smaller and have a 1.67x inference latency speedup, with no compromise to sparse model accuracy. In addition, DNNShifter has up to 11.9x lower overhead for switching models and up to 3.8x lower memory utilisation than existing approaches. DNNShifter is available for public use from https://github.com/blessonvar/DNNShifter.

Collaborative machine learning (CML) techniques, such as federated learning, have been proposed to train deep learning models across multiple mobile devices and a server. CML techniques are privacy-preserving as a local model that is trained on each device instead of the raw data from the device is shared with the server. However, CML training is inefficient due to low resource utilization. We identify idling resources on the server and devices due to sequential computation and communication as the principal cause of low resource utilization. A novel framework PiPar that leverages pipeline parallelism for CML techniques is developed to substantially improve resource utilization. A new training pipeline is designed to parallelize the computations on different hardware resources and communication on different bandwidth resources, thereby accelerating the training process in CML. A low overhead automated parameter selection method is proposed to optimize the pipeline, maximizing the utilization of available resources. The experimental results confirm the validity of the underlying approach of PiPar and highlight that when compared to federated learning: (i) the idle time of the server can be reduced by up to 64.1×, and (ii) the overall training time can be accelerated by up to 34.6× under varying network conditions for a collection of six small and large popular deep neural networks and four datasets without sacrificing accuracy. It is also experimentally demonstrated that PiPar achieves performance benefits when incorporating differential privacy methods and operating in environments with heterogeneous devices and changing bandwidths.

Efficiently running federated learning (FL) on resource-constrained devices is challenging since they are required to train computationally intensive deep neural networks (DNN) independently. DNN partitioning-based FL (DPFL) has been proposed as one mechanism to accelerate training where the layers of a DNN (or computation) are offloaded from the device to the server. However, this creates significant communication overheads since the intermediate activation and gradient need to be transferred between the device and the server during training. While current research reduces the communication introduced by DNN partitioning using local loss-based methods, we demonstrate that these methods are ineffective in improving the overall efficiency (communication overhead and training speed) of a DPFL system. This is because they suffer from accuracy degradation and ignore the communication costs incurred when transferring the activation from the device to the server. This article proposesEcoFed– a communication efficient framework for DPFL systems.EcoFedeliminates the transmission of the gradient by developing pre-trained initialization of the DNN model on the device for the first time. This reduces the accuracy degradation seen in local loss-based methods. In addition,EcoFedproposes a novel replay buffer mechanism and implements a quantization-based compression technique to reduce the transmission of the activation. It is experimentally demonstrated thatEcoFedcan reduce the communication cost by up to 133× and accelerate training by up to 21× when compared to classic FL. Compared to vanilla DPFL,EcoFedachieves a 16× communication reduction and 2.86× training time speed-up.

Ensemble Decision Systems offer a unique form of decision making that allows a collection of algorithms to reason together about a problem. Each individual algorithm has its own inherent strengths and weaknesses, and often it is difficult to overcome the weaknesses, while retaining the strengths. Instead of altering the properties of the algorithm, the Ensemble Decision System augments the performance with other algorithms that have complementing strengths. This work outlines different options for building an Ensemble Decision System as well as providing analysis on its performance compared to the individual components of the system with interesting results, showing an increase in the generality of the algorithms without significantly impeding performance.