Related papers: GreenDyGNN: Runtime-Adaptive Energy-Efficient Comm…

Graph Convolutional Networks (GCNs) is the state-of-the-art method for learning graph-structured data, and training large-scale GCNs requires distributed training across multiple accelerators such that each accelerator is able to hold a…

Deep learning has experienced significant growth in recent years, resulting in increased energy consumption and carbon emission from the use of GPUs for training deep neural networks (DNNs). Answering the call for sustainability,…

Predicting the effect of amino acid mutations on enzyme thermodynamic stability (DDG) is fundamental to protein engineering and drug design. While recent deep learning approaches have shown promise, they often process sequence and structure…

Dynamic Graph Neural Networks (DGNNs) have gained widespread attention due to their applicability in diverse domains such as traffic network prediction, epidemiological forecasting, and social network analysis. In this paper, we present…

Ensuring packet-level communication quality is vital for ultra-reliable, low-latency communications (URLLC) in large-scale industrial wireless networks. We enhance the Local Deadline Partition (LDP) algorithm by introducing a Graph…

Minimizing transmission delay in wireless multi-hop networks is a fundamental yet challenging task due to the complex coupling among interference, queue dynamics, and distributed control. Traditional scheduling algorithms, such as…

Training Graph Neural Networks (GNNs) on real-world graphs consisting of billions of nodes and edges is quite challenging, primarily due to the substantial memory needed to store the graph and its intermediate node and edge features, and…

Data parallelism has become a dominant method to scale Deep Neural Network (DNN) training across multiple nodes. Since synchronizing a large number of gradients of the local model can be a bottleneck for large-scale distributed training,…

Distributed training of GNNs enables learning on massive graphs (e.g., social and e-commerce networks) that exceed the storage and computational capacity of a single machine. To reach performance comparable to centralized training,…

In recent years, the use of artificial intelligence on resource-constrained IoT devices has grown significantly. However, existing approaches to DNN partitioning and offloading across the edge-cloud continuum typically rely on static…

Generative Artificial Intelligence (GAI) shows remarkable productivity and creativity in Mobile Edge Networks, such as the metaverse and the Industrial Internet of Things. Federated learning is a promising technique for effectively training…

Graph Neural Network (GNN) models on streaming graphs entail algorithmic challenges to continuously capture its dynamic state, as well as systems challenges to optimize latency, memory, and throughput during both inference and training. We…

Training Graph Neural Networks (GNN) on large graphs is resource-intensive and time-consuming, mainly due to the large graph data that cannot be fit into the memory of a single machine, but have to be fetched from distributed graph storage…

We address the efficiency issue for the construction of a deep graph neural network (GNN). The approach exploits the idea of representing each input graph as a fixed point of a dynamical system (implemented through a recurrent neural…

Inference for Deep Neural Networks is increasingly being executed locally on mobile and embedded platforms due to its advantages in latency, privacy and connectivity. Since modern System on Chips typically execute a combination of different…

Graph neural networks (GNNs) learn representations from network data with naturally distributed architectures, rendering them well-suited candidates for decentralized learning. Oftentimes, this decentralized graph support changes with time…

Bike sharing is a vital component of a modern multi-modal transportation system. However, its implementation can lead to bike supply-demand imbalance due to fluctuating spatial and temporal demands. This study proposes a comprehensive…

Training Graph Neural Networks (GNNs) on large graphs presents unique challenges due to the large memory and computing requirements. Distributed GNN training, where the graph is partitioned across multiple machines, is a common approach to…

We present a novel dynamic configuration technique for deep neural networks that permits step-wise energy-accuracy trade-offs during runtime. Our configuration technique adjusts the number of channels in the network dynamically depending on…

In recent years, graph neural networks (GNNs) have been widely applied in tackling combinatorial optimization problems. However, existing methods still suffer from limited accuracy when addressing that on complex graphs and exhibit poor…