Related papers: Off the Beaten Path: Let's Replace Term-Based Retr…
Graph Retrieval has witnessed continued interest and progress in the past few years. In thisreport, we focus on neural network based approaches for Graph matching and retrieving similargraphs from a corpus of graphs. We explore methods…
One of the core problems in large-scale recommendations is to retrieve top relevant candidates accurately and efficiently, preferably in sub-linear time. Previous approaches are mostly based on a two-step procedure: first learn an…
Graph neural networks (GNNs), as a group of powerful tools for representation learning on irregular data, have manifested superiority in various downstream tasks. With unstructured texts represented as concept maps, GNNs can be exploited…
Corporate credit underwriting requires analysts to extract actionable evidence from long, heterogeneous financial documents spanning hundreds of pages and multiple languages. Standard Retrieval-Augmented Generation (RAG) pipelines optimize…
Beam search is a go-to strategy for decoding neural sequence models. The algorithm can naturally be viewed as a subset optimization problem, albeit one where the corresponding set function does not reflect interactions between candidates.…
Many users turn to document retrieval systems (e.g. search engines) to seek answers to controversial questions. Answering such user queries usually require identifying responses within web documents, and aggregating the responses based on…
Khandelwal et al. (2020) use a k-nearest-neighbor (kNN) component to improve language model performance. We show that this idea is beneficial for open-domain question answering (QA). To improve the recall of facts encountered during…
Reverse k nearest neighbor (RkNN) queries are fundamental in spatial databases, location-based analytics, and recommendation systems. Existing state-of-the-art techniques rely on spatial pruning supported by R-trees and their variants.…
A $k$-nearest neighbor ($k$NN) query determines the $k$ nearest points, using distance metrics, from a specific location. An all $k$-nearest neighbor (A$k$NN) query constitutes a variation of a $k$NN query and retrieves the $k$ nearest…
The k Nearest Neighbors (kNN) method has received much attention in the past decades, where some theoretical bounds on its performance were identified and where practical optimizations were proposed for making it work fairly well in high…
In this vision paper, we propose a shift in perspective for improving the effectiveness of similarity search. Rather than focusing solely on enhancing the data quality, particularly machine learning-generated embeddings, we advocate for a…
Approximate nearest neighbor (ANN) search is a fundamental problem in many areas of data mining, machine learning and computer vision. The performance of traditional hierarchical structure (tree) based methods decreases as the…
Retrieval is a widely adopted approach for improving language models leveraging external information. As the field moves towards multi-modal large language models, it is important to extend the pure text based methods to incorporate other…
Approximate $k$-nearest neighbor search (A$k$-NNS) is a core operation in vector databases, underpinning applications such as retrieval-augmented generation (RAG) and image retrieval. In these scenarios, users often prefer diverse result…
Re-finding files from a personal computer is a frequent demand to users. When encountered a difficult re-finding task, people may not recall the attributes used by conventional re-finding methods, such as a file's path, file name, keywords…
Fixed-radius near neighbor search is a fundamental data operation that retrieves all data points within a user-specified distance to a query point. There are efficient algorithms that can provide fast approximate query responses, but they…
Feature means countenance, remote sensing scene objects with similar characteristics, associated to interesting scene elements in the image formation process. They are classified into three types in image processing, that is low, middle and…
Vector databases typically rely on approximate nearest neighbor (ANN) search to retrieve the top-k closest vectors to a query in embedding space. While effective, this approach often yields semantically redundant results, missing the…
Graph-based algorithms have demonstrated state-of-the-art performance in the nearest neighbor search (NN-Search) problem. These empirical successes urge the need for theoretical results that guarantee the search quality and efficiency of…
Retrieving semantically relevant documents in niche domains poses significant challenges for traditional TF-IDF-based systems, often resulting in low similarity scores and suboptimal retrieval performance. This paper addresses these…