Related papers: PathWeaver: A High-Throughput Multi-GPU System for…

Neural architecture search (NAS) has a great impact by automatically designing effective neural network architectures. However, the prohibitive computational demand of conventional NAS algorithms (e.g. $10^4$ GPU hours) makes it difficult…

In recent years, the CNNs have achieved great successes in the image processing tasks, e.g., image recognition and object detection. Unfortunately, traditional CNN's classification is found to be easily misled by increasingly complex image…

Hybrid search has emerged as a promising paradigm that combines lexical and semantic retrieval, enhancing accuracy for applications such as recommendations, information retrieval, and Retrieval-Augmented Generation. However, existing…

Approximate Nearest Neighbor Search (ANNS) on high-dimensional vectors has become a fundamental and essential component in various machine learning tasks. Recently, with the rapid development of deep learning models and the applications of…

On-disk graph-based approximate nearest neighbor search (ANNS) is essential for large-scale, high-dimensional vector retrieval, yet its performance is widely recognized to be limited by the prohibitive I/O costs. Interestingly, we observed…

Neural network (NN) models are increasingly used in scientific simulations, AI, and other high performance computing (HPC) fields to extract knowledge from datasets. Each dataset requires tailored NN model architecture, but designing…

This paper studies the neural architecture search (NAS) problem for developing efficient generator networks. Compared with deep models for visual recognition tasks, generative adversarial network (GAN) are usually designed to conduct…

Approximate nearest neighbor (ANN) search in high-dimensional metric spaces is a fundamental problem with many applications. Over the past decade, proximity graph (PG)-based indexes have demonstrated superior empirical performance over…

Effective and efficient graph representation learning is essential for enabling critical downstream tasks, such as node classification, link prediction, and subgraph search. However, existing graph neural network (GNN) architectures often…

We propose a generic feature compression method for Approximate Nearest Neighbor Search (ANNS) problems, which speeds up existing ANNS methods in a plug-and-play manner. Specifically, based on transformer, we propose a new network structure…

In the context of the genome-wide association studies (GWAS), one has to solve long sequences of generalized least-squares problems; such a task has two limiting factors: execution time --often in the range of days or weeks-- and data…

Graph neural networks (GNNs) are gaining increasing popularity as a promising approach to machine learning on graphs. Unlike traditional graph workloads where each vertex/edge is associated with a scalar, GNNs attach a feature tensor to…

Large scale-free graphs are famously difficult to process efficiently: the skewed vertex degree distribution makes it difficult to obtain balanced partitioning. Our research instead aims to turn this into an advantage by partitioning the…

Low-latency detections of gravitational waves (GWs) are crucial to enable prompt follow-up observations to astrophysical transients by conventional telescopes. We have developed a low-latency pipeline using a technique called Summed…

Breadth-First Search (BFS) is a building block used in a wide array of graph analytics and is used in various network analysis domains: social, road, transportation, communication, and much more. Over the last two decades, network sizes…

Advances in embedding models for text, image, audio, and video drive progress across multiple domains, including retrieval-augmented generation, recommendation systems, and others. Many of these applications require an efficient method to…

Large-scale approximate nearest neighbor search (ANN) has been gaining attention along with the latest machine learning researches employing ANNs. If the data is too large to fit in memory, it is necessary to search for the most similar…

Recently, Graph Neural Networks (GNNs) have become state-of-the-art algorithms for analyzing non-euclidean graph data. However, to realize efficient GNN training is challenging, especially on large graphs. The reasons are many-folded: 1)…

Many applications require to learn, mine, analyze and visualize large-scale graphs. These graphs are often too large to be addressed efficiently using conventional graph processing technologies. Many applications have requirements to…

Hierarchical Navigable Small World (HNSW) has demonstrated impressive accuracy and low latency for high-dimensional nearest neighbor searches. However, its high computational demands and irregular, large-volume data access patterns present…