Related papers: NAVIS: Concurrent Search and Update with Low Posit…
Approximate Nearest Neighbor Search (ANNS) has become a fundamental component in many real-world applications. Among various ANNS algorithms, graph-based methods are state-of-the-art. However, ANNS often suffers from a significant drop in…
One-shot neural architecture search (NAS) substantially improves the search efficiency by training one supernet to estimate the performance of every possible child architecture (i.e., subnet). However, the inconsistency of characteristics…
The neural architecture search (NAS) algorithm with reinforcement learning can be a powerful and novel framework for the automatic discovering process of neural architectures. However, its application is restricted by noncontinuous and…
Graph processing on GPUs is gaining momentum due to the high throughputs observed compared to traditional CPUs, attributed to the vast number of processing cores on GPUs that can exploit parallelism in graph analytics. This paper discusses…
We present AutoPose, a novel neural architecture search(NAS) framework that is capable of automatically discovering multiple parallel branches of cross-scale connections towards accurate and high-resolution 2D human pose estimation.…
We study a graph search problem in which a team of searchers attempts to find a mobile target located in a graph. Assuming that (a) the visibility field of the searchers is limited, (b) the searchers have unit speed and (c) the target has…
Disk-based graph indexes for approximate nearest neighbor search (ANNS) must serve latency-sensitive queries and throughput-demanding updates concurrently. We observe that over 40% of search-thread CPU time is spent stalling on disk I/O;…
Inspired by the classical fractional cascading technique, we introduce new techniques to speed up the following type of iterated search in 3D: The input is a graph $\mathbf{G}$ with bounded degree together with a set $H_v$ of 3D hyperplanes…
Nearest neighbor search plays a fundamental role in many disciplines such as multimedia information retrieval, data-mining, and machine learning. The graph-based search approaches show superior performance over other types of approaches in…
Approximate Nearest Neighbor Search (ANNS) is a crucial operation in databases and artificial intelligence. While graph-based ANNS methods like HNSW and NSG excel in performance, they assume uniform query distribution. However, in…
For approximate nearest neighbor search, graph-based algorithms have shown to offer the best trade-off between accuracy and search time. We propose the Dynamic Exploration Graph (DEG) which significantly outperforms existing algorithms in…
As the amount of data produced in society continues to grow at an exponential rate, modern applications are incurring significant performance and energy penalties due to high data movement between the CPU and memory/storage. While…
Human pose estimation has achieved significant progress in recent years. However, most of the recent methods focus on improving accuracy using complicated models and ignoring real-time efficiency. To achieve a better trade-off between…
Panoptic segmentation is posed as a new popular test-bed for the state-of-the-art holistic scene understanding methods with the requirement of simultaneously segmenting both foreground things and background stuff. The state-of-the-art…
The searching procedure of neural architecture search (NAS) is notoriously time consuming and cost prohibitive.To make the search space continuous, most existing gradient-based NAS methods relax the categorical choice of a particular…
Approximate Nearest Neighbor Search (ANNS) is a core primitive in modern AI systems, and graph-based methods currently offer the best accuracy-efficiency trade-off at scale. The workload is fundamentally memory-bound: graph traversal…
The success of deep neural networks relies on significant architecture engineering. Recently neural architecture search (NAS) has emerged as a promise to greatly reduce manual effort in network design by automatically searching for optimal…
Exact subgraph matching on large-scale graphs remains a challenging problem due to high computational complexity and distributed system constraints. Existing GNN-based path embedding (GNN-PE) frameworks achieve efficient exact matching on…
Graph Neural Networks (GNNs) have emerged as a cornerstone of deep learning, with most existing methods rooted in graph signal processing and diffusion equations to model message passing. However, these approaches inherently suffer from the…
Billion-scale high-dimensional approximate nearest neighbour (ANN) search has become an important problem for searching similar objects among the vast amount of images and videos available online. The existing ANN methods are usually…