Leon Wong

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 in turn reduces resource requirements. State-of-the-art pruning is based on coarse-grained methods. They are time-consuming and inherently remove critical model parameters, adversely impacting the quality of the pruned model. This paper introduces projection pruning, a novel fine-grained method for pruning LLMs. In addition, LLM projection pruning is enhanced by a new approach we refer to as composite projection pruning - the synergistic combination of unstructured pruning that retains accuracy and structured pruning that reduces model size. We develop Mosaic, a novel system to create and deploy pruned LLMs using composite projection pruning. Mosaic is evaluated using a range of performance and quality metrics on multiple hardware platforms, LLMs, and datasets. Mosaic is 7.19x faster in producing models than existing approaches. Mosaic models achieve up to 84.2% lower perplexity and 31.4% higher accuracy than models obtained from coarse-grained pruning. Up to 67% faster inference and 68% lower GPU memory use is noted for Mosaic models. Mosaic is available for public use from https://github.com/blessonvar/Mosaic

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 their substantial computing, memory and energy requirements for delivering performance that is comparable to cloud-based ML. Therefore, model compression techniques, such as pruning, have been considered. Existing pruning methods are problematic for edge ML since they: (1) Create compressed models that have limited runtime performance benefits (using unstructured pruning) or compromise the final model accuracy (using structured pruning), and (2) Require substantial compute resources and time for identifying a suitable compressed DNN model (using neural architecture search). In this paper, we explore a new avenue, referred to as Pruning-at-Initialization (PaI), using structured pruning to mitigate the above problems. We develop Reconvene, a system for rapidly generating pruned models suited for edge deployments using structured PaI. Reconvene systematically identifies and prunes DNN convolution layers that are least sensitive to structured pruning. Reconvene rapidly creates pruned DNNs within seconds that are up to 16.21x smaller and 2x faster while maintaining the same accuracy as an unstructured PaI counterpart.

Zihan Zhang, Leon Wong, Blesson Varghese

A Federated Learning (FL) system collaboratively trains neural networks across devices and a server but is limited by significant on-device computation costs. Split Federated Learning (SFL) systems mitigate this by offloading a block of layers of the network from the device to a server. However, in doing so, it introduces large communication overheads due to frequent exchanges of intermediate activations and gradients between devices and the server and reduces model accuracy for non-IID data. We propose Ampere, a novel collaborative training system that simultaneously minimizes on-device computation and device-server communication while improving model accuracy. Unlike SFL, which uses a global loss by iterative end-to-end training, Ampere develops unidirectional inter-block training to sequentially train the device and server block with a local loss, eliminating the transfer of gradients. A lightweight auxiliary network generation method decouples training between the device and server, reducing frequent intermediate exchanges to a single transfer, which significantly reduces the communication overhead. Ampere mitigates the impact of data heterogeneity by consolidating activations generated by the trained device block to train the server block, in contrast to SFL, which trains on device-specific, non-IID activations. Extensive experiments on multiple CNNs and transformers show that, compared to state-of-the-art SFL baseline systems, Ampere (i) improves model accuracy by up to 13.26% while reducing training time by up to 94.6%, (ii) reduces device-server communication overhead by up to 99.1% and on-device computation by up to 93.13%, and (iii) reduces standard deviation of accuracy by 53.39% for various non-IID degrees highlighting superior performance when faced with heterogeneous data.

Zihan Zhang, Leon Wong, Blesson Varghese

Federated learning (FL) systems facilitate distributed machine learning across a server and multiple devices. However, FL systems have low resource utilization limiting their practical use in the real world. This inefficiency primarily arises from two types of idle time: (i) task dependency between the server and devices, and (ii) stragglers among heterogeneous devices. This paper introduces FedOptima, a resource-optimized FL system designed to simultaneously minimize both types of idle time; existing systems do not eliminate or reduce both at the same time. FedOptima offloads the training of certain layers of a neural network from a device to server using three innovations. First, devices operate independently of each other using asynchronous aggregation to eliminate straggler effects, and independently of the server by utilizing auxiliary networks to minimize idle time caused by task dependency. Second, the server performs centralized training using a task scheduler that ensures balanced contributions from all devices, improving model accuracy. Third, an efficient memory management mechanism on the server increases scalability of the number of participating devices. Four state-of-the-art offloading-based and asynchronous FL methods are chosen as baselines. Experimental results show that compared to the best results of the baselines on convolutional neural networks and transformers on multiple lab-based testbeds, FedOptima (i) achieves higher or comparable accuracy, (ii) accelerates training by 1.9x to 21.8x, (iii) reduces server and device idle time by up to 93.9% and 81.8%, respectively, and (iv) increases throughput by 1.1x to 2.0x.