Search Results for author:
Found 72 papers, 18 papers with code
Mitigating Memory Wall Effects in CNN Engines with On-the-Fly Weights Generation
In this work, we investigate the implications in terms of CNN engine design for a class of models that introduce a pre-convolution stage to decompress the weights at run time.
TinyTrain: Deep Neural Network Training at the Extreme Edge
On-device training is essential for user personalisation and privacy.
L-DAWA: Layer-wise Divergence Aware Weight Aggregation in Federated Self-Supervised Visual Representation Learning
The ubiquity of camera-enabled devices has led to large amounts of unlabeled image data being produced at the edge.
FDAPT: Federated Domain-adaptive Pre-training for Language Models
We demonstrate that FDAPT can maintain competitive downstream task performance to the centralized baseline in both IID and non-IID situations.
FedVal: Different good or different bad in federated learning
In this paper, we present a novel approach FedVal for both robustness and fairness that does not require any additional information from clients that could raise privacy concerns and consequently compromise the integrity of the FL system.
vFedSec: Efficient Secure Aggregation for Vertical Federated Learning via Secure Layer
Most work in privacy-preserving federated learning (FL) has been focusing on horizontally partitioned datasets where clients share the same sets of features and can train complete models independently.
Are We There Yet? Product Quantization and its Hardware Acceleration
To address this issue, and to more fairly assess PQ in terms of hardware efficiency, we design the first custom hardware accelerator to evaluate the speed and efficiency of running PQ models.
Privacy in Multimodal Federated Human Activity Recognition
This work studies the impact of privacy in federated HAR at a user, environment, and sensor level.
Efficient Vertical Federated Learning with Secure Aggregation
The majority of work in privacy-preserving federated learning (FL) has been focusing on horizontally partitioned datasets where clients share the same sets of features and can train complete models independently.
Can Fair Federated Learning reduce the need for Personalisation?
For situations where the federated model provides a lower accuracy than a model trained entirely locally by a client, personalisation improves the accuracy of the pre-trained federated weights to be similar to or exceed those of the local client model.
Gradient-less Federated Gradient Boosting Trees with Learnable Learning Rates
Existing works on federated XGBoost in the horizontal setting rely on the sharing of gradients, which induce per-node level communication frequency and serious privacy concerns.
A Federated Learning Benchmark for Drug-Target Interaction
Aggregating pharmaceutical data in the drug-target interaction (DTI) domain has the potential to deliver life-saving breakthroughs.
NAWQ-SR: A Hybrid-Precision NPU Engine for Efficient On-Device Super-Resolution
In recent years, image and video delivery systems have begun integrating deep learning super-resolution (SR) approaches, leveraging their unprecedented visual enhancement capabilities while reducing reliance on networking conditions.
Meta-Learned Kernel For Blind Super-Resolution Kernel Estimation
Recent image degradation estimation methods have enabled single-image super-resolution (SR) approaches to better upsample real-world images.
Pex: Memory-efficient Microcontroller Deep Learning through Partial Execution
Embedded and IoT devices, largely powered by microcontroller units (MCUs), could be made more intelligent by leveraging on-device deep learning.
The Future of Consumer Edge-AI Computing
Deep Learning has proliferated dramatically across consumer devices in less than a decade, but has been largely powered through the hardware acceleration within isolated devices.
Match to Win: Analysing Sequences Lengths for Efficient Self-supervised Learning in Speech and Audio
Self-supervised learning (SSL) has proven vital in speech and audio-related applications.
Fluid Batching: Exit-Aware Preemptive Serving of Early-Exit Neural Networks on Edge NPUs
With deep neural networks (DNNs) emerging as the backbone in a multitude of computer vision tasks, their adoption in real-world applications broadens continuously.
Adaptable Butterfly Accelerator for Attention-based NNs via Hardware and Algorithm Co-design
By jointly optimizing the algorithm and hardware, our FPGA-based butterfly accelerator achieves 14. 2 to 23. 2 times speedup over state-of-the-art accelerators normalized to the same computational budget.
Protea: Client Profiling within Federated Systems using Flower
Federated Learning (FL) has emerged as a prospective solution that facilitates the training of a high-performing centralised model without compromising the privacy of users.
Multi-DNN Accelerators for Next-Generation AI Systems
As the use of AI-powered applications widens across multiple domains, so do increase the computational demands.
Secure Aggregation for Federated Learning in Flower
Federated Learning (FL) allows parties to learn a shared prediction model by delegating the training computation to clients and aggregating all the separately trained models on the server.
Federated Self-supervised Speech Representations: Are We There Yet?
The ubiquity of microphone-enabled devices has lead to large amounts of unlabelled audio data being produced at the edge.
Differentiable Network Pruning for Microcontrollers
Embedded and personal IoT devices are powered by microcontroller units (MCUs), whose extreme resource scarcity is a major obstacle for applications relying on on-device deep learning inference.
Smart at what cost? Characterising Mobile Deep Neural Networks in the wild
To this end, we analyse over 16k of the most popular apps in the Google Play Store to characterise their DNN usage and performance across devices of different capabilities, both across tiers and generations.
Learn2Agree: Fitting with Multiple Annotators without Objective Ground Truth
For such issues, we propose a novel Learning to Agreement (Learn2Agree) framework to tackle the challenge of learning from multiple annotators without objective ground truth.
Temporal Kernel Consistency for Blind Video Super-Resolution
Deep learning-based blind super-resolution (SR) methods have recently achieved unprecedented performance in upscaling frames with unknown degradation.
Zero-Cost Operation Scoring in Differentiable Architecture Search
From this perspective, we introduce a novel \textit{perturbation-based zero-cost operation scoring} (Zero-Cost-PT) approach, which utilizes zero-cost proxies that were recently studied in multi-trial NAS but degrade significantly on larger search spaces, typical for differentiable NAS.
Adaptive Inference through Early-Exit Networks: Design, Challenges and Directions
DNNs are becoming less and less over-parametrised due to recent advances in efficient model design, through careful hand-crafted or NAS-based methods.
Deep Neural Network-based Enhancement for Image and Video Streaming Systems: A Survey and Future Directions
In recent years, advances in the field of deep learning on tasks such as super-resolution and image enhancement have led to unprecedented performance in generating high-quality images from low-quality ones, a process we refer to as neural enhancement.
Multi-Exit Semantic Segmentation Networks
At the same time, the heterogeneous capabilities of the target platforms and the diverse constraints of different applications require the design and training of multiple target-specific segmentation models, leading to excessive maintenance costs.
End-to-End Speech Recognition from Federated Acoustic Models
Training Automatic Speech Recognition (ASR) models under federated learning (FL) settings has attracted a lot of attention recently.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+2
DynO: Dynamic Onloading of Deep Neural Networks from Cloud to Device
Recently, there has been an explosive growth of mobile and embedded applications using convolutional neural networks(CNNs).
On-device Federated Learning with Flower
Federated Learning (FL) allows edge devices to collaboratively learn a shared prediction model while keeping their training data on the device, thereby decoupling the ability to do machine learning from the need to store data in the cloud.
Do We Need Anisotropic Graph Neural Networks?
We demonstrate that EGC outperforms existing approaches across 6 large and diverse benchmark datasets, and conclude by discussing questions that our work raise for the community going forward.
Ranked #11 on
Graph Property Prediction
on ogbg-code2
unzipFPGA: Enhancing FPGA-based CNN Engines with On-the-Fly Weights Generation
Single computation engines have become a popular design choice for FPGA-based convolutional neural networks (CNNs) enabling the deployment of diverse models without fabric reconfiguration.
FjORD: Fair and Accurate Federated Learning under heterogeneous targets with Ordered Dropout
FjORD alleviates the problem of client system heterogeneity by tailoring the model width to the client's capabilities.
A first look into the carbon footprint of federated learning
Despite impressive results, deep learning-based technologies also raise severe privacy and environmental concerns induced by the training procedure often conducted in data centers.
It's always personal: Using Early Exits for Efficient On-Device CNN Personalisation
On-device machine learning is becoming a reality thanks to the availability of powerful hardware and model compression techniques.
Zero-Cost Proxies for Lightweight NAS
For example, Spearman's rank correlation coefficient between final validation accuracy and our best zero-cost proxy on NAS-Bench-201 is 0. 82, compared to 0. 61 for EcoNAS (a recently proposed reduced-training proxy).
Leveraging Activity Recognition to Enable Protective Behavior Detection in Continuous Data
Protective behavior exhibited by people with chronic pain (CP) during physical activities is the key to understanding their physical and emotional states.
$μ$NAS: Constrained Neural Architecture Search for Microcontrollers
IoT devices are powered by microcontroller units (MCUs) which are extremely resource-scarce: a typical MCU may have an underpowered processor and around 64 KB of memory and persistent storage, which is orders of magnitude fewer computational resources than is typically required for deep learning.
Deep Learning in the Era of Edge Computing: Challenges and Opportunities
The era of edge computing has arrived.
Can Federated Learning Save The Planet?
Then, we compare the carbon footprint of FL to traditional centralized learning.
Neural Enhancement in Content Delivery Systems: The State-of-the-Art and Future Directions
In recent years, advances in the field of deep learning on tasks such as super-resolution and image enhancement have led to unprecedented performance in generating high-quality images from low-quality ones, a process we refer to as neural enhancement.
Libri-Adapt: A New Speech Dataset for Unsupervised Domain Adaptation
This paper introduces a new dataset, Libri-Adapt, to support unsupervised domain adaptation research on speech recognition models.
SPINN: Synergistic Progressive Inference of Neural Networks over Device and Cloud
Despite the soaring use of convolutional neural networks (CNNs) in mobile applications, uniformly sustaining high-performance inference on mobile has been elusive due to the excessive computational demands of modern CNNs and the increasing diversity of deployed devices.
Bunched LPCNet : Vocoder for Low-cost Neural Text-To-Speech Systems
LPCNet is an efficient vocoder that combines linear prediction and deep neural network modules to keep the computational complexity low.
Degree-Quant: Quantization-Aware Training for Graph Neural Networks
Graph neural networks (GNNs) have demonstrated strong performance on a wide variety of tasks due to their ability to model non-uniform structured data.
HAPI: Hardware-Aware Progressive Inference
Convolutional neural networks (CNNs) have recently become the state-of-the-art in a diversity of AI tasks.
Iterative Compression of End-to-End ASR Model using AutoML
Increasing demand for on-device Automatic Speech Recognition (ASR) systems has resulted in renewed interests in developing automatic model compression techniques.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+3
Flower: A Friendly Federated Learning Research Framework
Federated Learning (FL) has emerged as a promising technique for edge devices to collaboratively learn a shared prediction model, while keeping their training data on the device, thereby decoupling the ability to do machine learning from the need to store the data in the cloud.
BRP-NAS: Prediction-based NAS using GCNs
What is more, we investigate prediction quality on different metrics and show that sample efficiency of the predictor-based NAS can be improved by considering binary relations of models and an iterative data selection strategy.
Journey Towards Tiny Perceptual Super-Resolution
Recent works in single-image perceptual super-resolution (SR) have demonstrated unprecedented performance in generating realistic textures by means of deep convolutional networks.
IMUTube: Automatic Extraction of Virtual on-body Accelerometry from Video for Human Activity Recognition
The lack of large-scale, labeled data sets impedes progress in developing robust and generalized predictive models for on-body sensor-based human activity recognition (HAR).
Mic2Mic: Using Cycle-Consistent Generative Adversarial Networks to Overcome Microphone Variability in Speech Systems
A major challenge in building systems that combine audio models with commodity microphones is to guarantee their accuracy and robustness in the real-world.
Best of Both Worlds: AutoML Codesign of a CNN and its Hardware Accelerator
We automate HW-CNN codesign using NAS by including parameters from both the CNN model and the HW accelerator, and we jointly search for the best model-accelerator pair that boosts accuracy and efficiency.
The Final Frontier: Deep Learning in Space
Machine learning, particularly deep learning, is being increasing utilised in space applications, mirroring the groundbreaking success in many earthbound problems.
Are Accelerometers for Activity Recognition a Dead-end?
Overall, our work highlights the need to move away from accelerometers and calls for further exploration of using imagers for activity recognition.
EMOPAIN Challenge 2020: Multimodal Pain Evaluation from Facial and Bodily Expressions
The EmoPain 2020 Challenge is the first international competition aimed at creating a uniform platform for the comparison of machine learning and multimedia processing methods of automatic chronic pain assessment from human expressive behaviour, and also the identification of pain-related behaviours.
Neural networks on microcontrollers: saving memory at inference via operator reordering
Designing deep learning models for highly-constrained hardware would allow imbuing many edge devices with intelligence.
Multi-Step Decentralized Domain Adaptation
Despite the recent breakthroughs in unsupervised domain adaptation (uDA), no prior work has studied the challenges of applying these methods in practical machine learning scenarios.
MobiSR: Efficient On-Device Super-Resolution through Heterogeneous Mobile Processors
In recent years, convolutional networks have demonstrated unprecedented performance in the image restoration task of super-resolution (SR).
ShrinkML: End-to-End ASR Model Compression Using Reinforcement Learning
Our results show that in the absence of retraining our RL-based search is an effective and practical method to compress a production-grade ASR system.
Automatic Speech Recognition
Automatic Speech Recognition (ASR)
+6
EmBench: Quantifying Performance Variations of Deep Neural Networks across Modern Commodity Devices
In recent years, advances in deep learning have resulted in unprecedented leaps in diverse tasks spanning from speech and object recognition to context awareness and health monitoring.
An Empirical study of Binary Neural Networks' Optimisation
In this work, we empirically identify and study the effectiveness of the various ad-hoc techniques commonly used in the literature, providing best-practices for efficient training of binary models.
Learning Bodily and Temporal Attention in Protective Movement Behavior Detection
For people with chronic pain, the assessment of protective behavior during physical functioning is essential to understand their subjective pain-related experiences (e. g., fear and anxiety toward pain and injury) and how they deal with such experiences (avoidance or reliance on specific body joints), with the ultimate goal of guiding intervention.
Chronic-Pain Protective Behavior Detection with Deep Learning
In chronic pain rehabilitation, physiotherapists adapt physical activity to patients' performance based on their expression of protective behavior, gradually exposing them to feared but harmless and essential everyday activities.
Privacy-Preserving Deep Inference for Rich User Data on The Cloud
Our evaluations show that by using certain kind of fine-tuning and embedding techniques and at a small processing costs, we can greatly reduce the level of information available to unintended tasks applied to the data feature on the cloud, and hence achieving the desired tradeoff between privacy and performance.
Cross-modal Recurrent Models for Weight Objective Prediction from Multimodal Time-series Data
We analyse multimodal time-series data corresponding to weight, sleep and steps measurements.
A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics
To this end, instead of performing the whole operation on the cloud, we let an IoT device to run the initial layers of the neural network, and then send the output to the cloud to feed the remaining layers and produce the final result.
X-CNN: Cross-modal Convolutional Neural Networks for Sparse Datasets
In this paper we propose cross-modal convolutional neural networks (X-CNNs), a novel biologically inspired type of CNN architectures, treating gradient descent-specialised CNNs as individual units of processing in a larger-scale network topology, while allowing for unconstrained information flow and/or weight sharing between analogous hidden layers of the network---thus generalising the already well-established concept of neural network ensembles (where information typically may flow only between the output layers of the individual networks).
