Search
Results
-
Localised Adaptive Spatial-Temporal Graph Neural Network
(2023)KDD '23: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data MiningSpatial-temporal graph models are prevailing for abstracting and modelling spatial and temporal dependencies. In this work, we ask the following question: whether and to what extent can we localise spatial-temporal graph models? We limit our scope to adaptive spatial-temporal graph neural networks (ASTGNNs), the state-of-the-art model architecture. Our approach to localisation involves sparsifying the spatial graph adjacency matrices. To ...Conference Paper -
Combating Distribution Shift for Accurate Time Series Forecasting via Hypernetworks
(2023)2022 IEEE 28th International Conference on Parallel and Distributed Systems (ICPADS)Time series forecasting has widespread applications in urban life ranging from air quality monitoring to traffic analysis. However, accurate time series forecasting is challenging because real-world time series suffer from the distribution shift problem, where their statistical properties change over time. Despite extensive solutions to distribution shifts in domain adaptation or generalization, they fail to function effectively in unknown, ...Conference Paper -
BUTLER: Increasing the Availability of Low-Power Wireless Communication Protocols
(2023)EWSN '22: Proceedings of the 2022 International Conference on Embedded Wireless Systems and NetworksOver the past years, various low-power wireless protocols based on synchronous transmissions (ST) have been developed to meet the high dependability requirements of emerging cyber-physical applications. For example, Wireless Paxos provides consensus, a key mechanism for building fault-tolerant systems through replication. However, Wireless Paxos and other ST-based protocols are themselves not fault-tolerant: They suffer from a single point ...Conference Paper -
Energy-Efficient Bootstrapping in Multi-hop Harvesting-Based Networks
(2023)2023 18th Wireless On-Demand Network Systems and Services Conference (WONS)Short-range multi-hop communication is an energy-efficient way to collect, share, and distribute large amounts of data with Internet of Things (IoT) systems. Nevertheless, the resource demands of wireless communication impose a burden on battery-operated IoT nodes, limiting their lifetime. Energy harvesting can address the energy limitation but introduces significant power variability, which affects reliable operation causing nodes to ...Conference Paper -
Stitching Weight-Shared Deep Neural Networks for Efficient Multitask Inference on GPU
(2022)2022 19th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON)Intelligent personal and home applications demand multiple deep neural networks (DNNs) running on resource-constrained platforms for compound inference tasks, known as multitask inference. To fit multiple DNNs into low-resource devices, emerging techniques resort to weight sharing among DNNs to reduce their storage. However, such reduction in storage fails to translate into efficient execution on common accelerators such as GPUs. Most DNN ...Conference Paper -
Accurate Onboard Predictions for Indoor Energy Harvesting using Random Forests
(2022)2022 11th Mediterranean Conference on Embedded Computing (MECO)Indoor energy harvesting has recently enabled long-term deployments of sustainable IoT sensor nodes. The performance of such systems operating in an energy-neutral manner can be optimized by exploiting energy prediction models. Numerous prediction algorithms have been developed, yet they are primarily intended for outdoor (solar) energy harvesting. Indoor environments are much more challenging to predict since the primary energy is very ...Conference Paper -
Pruning Meta-Trained Networks for On-Device Adaptation
(2021)Proceedings of the 30th ACM International Conference on Information & Knowledge ManagementAdapting neural networks to unseen tasks with few training samples on resource-constrained devices benefits various Internet-of-Things applications. Such neural networks should learn the new tasks in few shots and be compact in size. Meta-learning enables few-shot learning, yet the meta-trained networks can be over-parameterised. However, naive combination of standard compression techniques like network pruning with meta-learning jeopardises ...Conference Paper -
TIP-Air: Tracking Pollution Transfer for Accurate Air Quality Prediction
(2021)Adjunct Proceedings of the 2021 ACM International Joint Conference on Pervasive and Ubiquitous Computing and Proceedings of the 2021 ACM International Symposium on Wearable Computers (UbiComp-ISWC '21 Adjunct)Air quality is of vital importance to human health. Accurately predicting air quality, especially its sudden changes, is highly valuable for citizens and governments to make personal and local decisions, design intelligent policies and control pollution at minimal cost. However, none of the existing methods achieves sufficient prediction accuracy for time intervals of sudden pollution change due to inability of existing models to take ...Conference Paper -
Pruning-Aware Merging for Efficient Multitask Inference
(2021)Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining (KDD '21)Many mobile applications demand selective execution of multiple correlated deep learning inference tasks on resource-constrained platforms. Given a set of deep neural networks, each pre-trained for a single task, it is desired that executing arbitrary combinations of tasks yields minimal computation cost. Pruning each network separately yields suboptimal computation cost due to task relatedness. A promising remedy is to merge the networks ...Conference Paper -
HiMap: Fast and Scalable High-Quality Mapping on CGRA via Hierarchical Abstraction
(2021)Proceedings of the 2021 Design, Automation & Test in Europe (DATE 2021)Coarse-Grained Reconfigurable Array (CGRA) has emerged as a promising hardware accelerator due to the excellent balance among reconfigurability, performance, and energy efficiency. The CGRA performance strongly depends on a high-quality compiler to map the application kernels on the architecture. Unfortunately, the state-of-the-art compilers fall short in generating high quality mapping within an acceptable compilation time, especially ...Conference Paper