ANNLib: A Development Framework for Efficient Approximate Nearest Neighbor Search

• URL: http://arxiv.org/abs/2607.17582v1
• Date: Mon, 20 Jul 2026 05:59:59 GMT
• Title: ANNLib: A Development Framework for Efficient Approximate Nearest Neighbor Search
• Abstract summary: ANNLib is a library that provides a programming framework for achieving high performance and flexible functionality in ANNS systems.<n>We carefully decouple and independently optimize both the algorithm and the data structure components of an ANNS system.<n>In addition, we integrate state-of-the-art algorithms and data structures into ANNLib as modules, along with our new designs.
• Score: 1.7987122293401787
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Approximate Nearest Neighbor Search (ANNS) plays a pivotal role in modern deep learning pipelines. Recently, many ANNS systems have been proposed to either provide broad functionality or reach high performance. However, it is yet difficult to achieve both with minimal programming efforts. We propose ANNLib to address the gap. ANNLib is a library that provides a programming framework for achieving high performance and flexible functionality in ANNS systems, based on popular graph-based ANNS algorithms. We carefully decouple and independently optimize both the algorithm and the data structure components of an ANNS system. In addition, we integrate state-of-the-art algorithms and data structures into ANNLib as modules, along with our new designs. Users can choose combinations of components to implement sophisticated settings with high performance, such as filter search, fully dynamic updates, and historical queries on snapshots. Our experiments show that our new solution provides a simple interface for various applications and achieves comparable or even better performance than previous work, specifically for each application.

Related papers

• LM-Searcher: Cross-domain Neural Architecture Search with LLMs via Unified Numerical Encoding [55.5535016040221]
  LM-Searcher is a novel framework for cross-domain neural architecture optimization.<n>Central to our approach is NCode, a universal numerical string representation for neural architectures.<n>Our dataset, encompassing a wide range of architecture-performance pairs, encourages robust and transferable learning.
  arXiv  Detail & Related papers  (2025-09-06T09:26:39Z)
• PLANETALIGN: A Comprehensive Python Library for Benchmarking Network Alignment [51.927788705342266]
  Network alignment (NA) aims to identify node correspondence across different networks.<n>Despite growing research in NA, there lacks a comprehensive library that facilitates the systematic development and benchmarking of NA methods.<n>We introduce PLANETALIGN, a Python library for network alignment that features a rich collection of built-in datasets, methods, and evaluation pipelines.
  arXiv  Detail & Related papers  (2025-05-27T15:56:30Z)
• kANNolo: Sweet and Smooth Approximate k-Nearest Neighbors Search [5.394883109521642]
  Approximate Nearest Neighbors (ANN) search is a crucial task in several applications like recommender systems and information retrieval.<n>Current state-of-the-art ANN libraries, although being performance-oriented, often lack modularity and ease of use.<n>We introduce kANNolo, a novel research-oriented ANN library written in Rust and explicitly designed to combine usability with performance effectively.
  arXiv  Detail & Related papers  (2025-01-10T17:19:59Z)
• Combining Neural Architecture Search and Automatic Code Optimization: A Survey [0.8796261172196743]
  Two notable techniques are Hardware-aware Neural Architecture Search (HW-NAS) and Automatic Code Optimization (ACO) HW-NAS automatically designs accurate yet hardware-friendly neural networks, while ACO involves searching for the best compiler optimizations to apply on neural networks. This survey explores recent works that combine these two techniques within a single framework.
  arXiv  Detail & Related papers  (2024-08-07T22:40:05Z)
• Model Input-Output Configuration Search with Embedded Feature Selection for Sensor Time-series and Image Classification [0.0]
  MICS-EFS is a model input-output configuration search with embedded feature selection.<n>It delivers an average accuracy improvement of 1.5% over baseline models.<n>It reduces feature dimensionality to just 2-5% of the original data, significantly enhancing computational efficiency.
  arXiv  Detail & Related papers  (2023-10-26T08:58:29Z)
• PLiNIO: A User-Friendly Library of Gradient-based Methods for Complexity-aware DNN Optimization [3.460496851517031]
  PLiNIO is an open-source library implementing a comprehensive set of state-of-the-art DNN design automation techniques. We show that PLiNIO achieves up to 94.34% memory reduction for a 1% accuracy drop compared to a baseline architecture.
  arXiv  Detail & Related papers  (2023-07-18T07:11:14Z)
• Flexible Channel Dimensions for Differentiable Architecture Search [50.33956216274694]
  We propose a novel differentiable neural architecture search method with an efficient dynamic channel allocation algorithm. We show that the proposed framework is able to find DNN architectures that are equivalent to previous methods in task accuracy and inference latency.
  arXiv  Detail & Related papers  (2023-06-13T15:21:38Z)
• OFA$^2$: A Multi-Objective Perspective for the Once-for-All Neural Architecture Search [79.36688444492405]
  Once-for-All (OFA) is a Neural Architecture Search (NAS) framework designed to address the problem of searching efficient architectures for devices with different resources constraints. We aim to give one step further in the search for efficiency by explicitly conceiving the search stage as a multi-objective optimization problem.
  arXiv  Detail & Related papers  (2023-03-23T21:30:29Z)
• Searching Large Neighborhoods for Integer Linear Programs with Contrastive Learning [39.40838358438744]
  Linear Programs (ILPs) are powerful tools for modeling and solving a large number of optimization problems. Large Neighborhood Search (LNS), as a algorithm, can find high quality solutions to ILPs faster than Branch and Bound. We propose a novel approach, CL-LNS, that delivers state-of-the-art anytime performance on several ILP benchmarks measured by metrics.
  arXiv  Detail & Related papers  (2023-02-03T07:15:37Z)
• One-Shot Neural Ensemble Architecture Search by Diversity-Guided Search Space Shrinking [97.60915598958968]
  We propose a one-shot neural ensemble architecture search (NEAS) solution that addresses the two challenges. For the first challenge, we introduce a novel diversity-based metric to guide search space shrinking. For the second challenge, we enable a new search dimension to learn layer sharing among different models for efficiency purposes.
  arXiv  Detail & Related papers  (2021-04-01T16:29:49Z)
• EDD: Efficient Differentiable DNN Architecture and Implementation Co-search for Embedded AI Solutions [40.32848001349242]
  We propose a fully simultaneous, efficient differentiable DNN architecture and implementation co-search (EDD) methodology. We formulate the co-search problem by fusing search variables and hardware implementation variables into one solution space, and maximize both algorithm accuracy and hardware implementation quality.
  arXiv  Detail & Related papers  (2020-05-06T02:37:48Z)
• DDPNAS: Efficient Neural Architecture Search via Dynamic Distribution Pruning [135.27931587381596]
  We propose an efficient and unified NAS framework termed DDPNAS via dynamic distribution pruning. In particular, we first sample architectures from a joint categorical distribution. Then the search space is dynamically pruned and its distribution is updated every few epochs. With the proposed efficient network generation method, we directly obtain the optimal neural architectures on given constraints.
  arXiv  Detail & Related papers  (2019-05-28T06:35:52Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.