Related papers: Learned Low Precision Graph Neural Networks

Neural architecture search (NAS) and network pruning are widely studied efficient AI techniques, but not yet perfect. NAS performs exhaustive candidate architecture search, incurring tremendous search cost. Though (structured) pruning can…

Approximate nearest neighbor (ANN) search in high dimensions is an integral part of several computer vision systems and gains importance in deep learning with explicit memory representations. Since PQT, FAISS, and SONG started to leverage…

Graph Neural Networks (GNNs) have demonstrated remarkable success in various applications, yet they often struggle to capture long-range dependencies (LRD) effectively. This paper introduces GraphMinNet, a novel GNN architecture that…

Early neural network architectures were designed by so-called "grad student descent". Since then, the field of Neural Architecture Search (NAS) has developed with the goal of algorithmically designing architectures tailored for a dataset of…

In massive multi-input multi-output (MIMO) systems, the main bottlenecks of location- and orientation-assisted beam alignment using deep neural networks (DNNs) are large training overhead and significant performance degradation. This paper…

Network architecture search (NAS) achieves state-of-the-art results in various tasks such as classification and semantic segmentation. Recently, a reinforcement learning-based approach has been proposed for Generative Adversarial Networks…

Graph Neural Networks (GNNs) play a pivotal role in graph-based tasks for their proficiency in representation learning. Among the various GNN methods, spectral GNNs employing polynomial filters have shown promising performance on tasks…

We consider learning deep neural networks (DNNs) that consist of low-precision weights and activations for efficient inference of fixed-point operations. In training low-precision networks, gradient descent in the backward pass is performed…

While Graph Neural Networks (GNNs) excel on graph-structured data, their performance is fundamentally limited by the quality of the observed graph, which often contains noise, missing links, or structural properties misaligned with GNNs'…

Traditional Deep Neural Network (DNN) quantization methods using integer, fixed-point, or floating-point data types struggle to capture diverse DNN parameter distributions at low precision, and often require large silicon overhead and…

Graph Neural Networks (GNNs) have proved to be an effective representation learning framework for graph-structured data, and have achieved state-of-the-art performance on many practical predictive tasks, such as node classification, link…

Neural architecture search (NAS) recently attracts much research attention because of its ability to identify better architectures than handcrafted ones. However, many NAS methods, which optimize the search process in a discrete search…

Graph Neural Networks (GNNs) are a promising deep learning approach for circumventing many real-world problems on graph-structured data. However, these models usually have at least one of four fundamental limitations: over-smoothing,…

Enabling efficient deep neural network (DNN) inference on edge devices with different hardware constraints is a challenging task that typically requires DNN architectures to be specialized for each device separately. To avoid the huge…

Neural architecture search (NAS) enables the automatic design of neural network models. However, training the candidates generated by the search algorithm for performance evaluation incurs considerable computational overhead. Our method,…

Graph Neural Networks (GNNs) have already been widely applied in various graph mining tasks. However, they suffer from the shallow architecture issue, which is the key impediment that hinders the model performance improvement. Although…

In the past few years, neural architecture search (NAS) has become an increasingly important tool within the deep learning community. Despite the many recent successes of NAS, however, most existing approaches operate within highly…

Graph neural networks (GNNs) are a well-regarded tool for learned control of networked dynamical systems due to their ability to be deployed in a distributed manner. However, current distributed GNN architectures assume that all nodes in…

Graph Neural Networks (GNNs) are becoming increasingly popular for vision-based applications due to their intrinsic capacity in modeling structural and contextual relations between various parts of an image frame. On another front, the…

Graph neural networks (GNNs) are a class of deep models that operate on data with arbitrary topology represented as graphs. We introduce an efficient memory layer for GNNs that can jointly learn node representations and coarsen the graph.…