Research map / Learning theory and algorithms / Prediction and decision losses

Fast Diverse Nearest Neighbor Search

NeurIPS 2026 · Learning theory and algorithms › Prediction and decision losses · approach: Approximate nearest neighbor indexing

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Studies k-diverse nearest neighbor search, retrieving k approximate nearest neighbors with distinct colors for a query, to support diversity-aware retrieval.

Problem

Retrieving k approximate nearest neighbors with distinct colors (categories) for a query point in a colored dataset, as needed for diversity in retrieval tasks such as recommending products from different sellers.

Approach

Abstract is truncated; the stated focus is a faster approach to k-diverse nearest neighbor search than previous state-of-the-art methods, but the specific technique is not stated in the available text.

Closest papers by meaning

• Graph-Based Algorithms for Diverse Similarity Search (ICML 2025 · similarity 0.92)
• Welfarist Formulations for Diverse Similarity Search (ICLR 2026 · similarity 0.89)
• Worst-case Performance of Popular Approximate Nearest Neighbor Search Implementations: Guarantees and Limitations (NeurIPS 2023 · similarity 0.88)
• LotusFilter: Fast Diverse Nearest Neighbor Search via a Learned Cutoff Table (CVPR 2025 · similarity 0.86)
• Sort Before You Prune: Improved Worst-Case Guarantees of the DiskANN Family of Graphs (ICML 2025 · similarity 0.85)
• Distance Adaptive Beam Search for Provably Accurate Graph-Based Nearest Neighbor Search (NeurIPS 2025 · similarity 0.85)