arXiv subjects

Daichi Amagata

Publications and source records attributed to Daichi Amagata.

16 recordsLinked to original sources

arXiv2026

Duration-constrained Interval Joins

Many databases, including temporal, uncertain, spatial, and trajectory databases, use interval data, and interval joins are among the most frequently used operators. Many studies proposed efficient interval join algorithms, but they do not consider the overlap duration. They return any pairs of intervals, even if they overlap very slightly, e.g., with no essential correlation or relationship. Subsequent applications may suffer from such interval pairs, as they may be noise or unnecessary for the analysis. Furthermore, outputting such pairs also increases join time. To address the above issues, this paper addresses the problem of duration-constrained interval join. Given two interval collections $R$ and $S$ and an overlap duration constraint $\epsilon$, this problem returns all interval pairs $(r,s)$ such that $r \in R$, $s \in S$, and the overlap duration between $r$ and $s$ is at least $\epsilon$. A straightforward approach for this problem is to run a state-of-the-art interval join algorithm and then filter qualified interval pairs. However, this is inefficient, as it generates unnecessary interval pairs and incurs duration computations, which cannot overcome the above efficiency concern. We propose an efficient algorithm for this problem that removes the above drawback. Furthermore, we propose two optimization techniques to improve the efficiency of our algorithm. We conduct extensive experiments on three real-world interval datasets, and the results demonstrate that our algorithm outperforms existing techniques applicable to our problem.

cs.DB↗

arXiv2026

Simple and Fast Algorithm for Graph-based Filtered Approximate Nearest Neighbor Search (Full Version)

It has been common to represent many objects as high-dimensional vectors due to the proliferation of machine learning-based embedding techniques. One of the most important functions for analyzing high-dimensional vectors is approximate nearest neighbor search, which, given a query vector, retrieves the vector that is approximately the most similar to the query vector. In many real-world applications, such as e-commerce, objects have not only vectors but also attributes, e.g., category, color, and brand, and they require a scenario where users can specify a query vector and a value for each attribute of interest. This problem, called filtered approximate nearest neighbor search, retrieves approximate nearest neighbors from a set of objects that have the specified attribute values. Efficiently solving this problem is challenging because it has to accept arbitrary query vectors and attribute values, which are not known in advance. Existing techniques suffer from slow search performance and difficulty in dealing with arbitrary combinations of attributes. This work overcomes these challenges and proposes a new algorithm for this problem. We conduct extensive experiments, and the results demonstrate the efficiency of our algorithm.

cs.DB↗

arXiv2025

How Should We Evaluate Data Deletion in Graph-Based ANN Indexes?

Approximate Nearest Neighbor Search (ANNS) has recently gained significant attention due to its many applications, such as Retrieval-Augmented Generation. Such applications require ANNS algorithms that support dynamic data, so the ANNS problem on dynamic data has attracted considerable interest. However, a comprehensive evaluation methodology for data deletion in ANNS has yet to be established. This study proposes an experimental framework and comprehensive evaluation metrics to assess the efficiency of data deletion for ANNS indexes under practical use cases. Specifically, we categorize data deletion methods in graph-based ANNS into three approaches and formalize them mathematically. The performance is assessed in terms of accuracy, query speed, and other relevant metrics. Finally, we apply the proposed evaluation framework to Hierarchical Navigable Small World, one of the state-of-the-art ANNS methods, to analyze the effects of data deletion, and propose Deletion Control, a method which dynamically selects the appropriate deletion method under a required search accuracy.

cs.LG↗

arXiv2025

Random Sampling over Spatial Range Joins

Spatial range joins have many applications, including geographic information systems, location-based social networking services, neuroscience, and visualization. However, joins incur not only expensive computational costs but also too large result sets. A practical and reasonable approach to alleviating these issues is to return random samples of the join results. Although this is promising and sufficient for many applications involving spatial range joins, efficiently computing random samples is not trivial. This is because we must obtain random join samples without running spatial range joins. We address this challenging problem for the first time and aim at designing a time- and space-efficient algorithm. First, we design two baseline algorithms that employ existing techniques for random sampling and show that they are not efficient. Then, we propose a new data structure that can deal with our problem in $\tilde{O}(n + m + t)$ expected time and $O(n+m)$ space, where $n$ and $m$ are the sizes of two point sets and $t$ is the required number of samples. We conduct extensive experiments using four real spatial datasets, and the results demonstrate that our algorithm is significantly faster than the baselines in most tests.

cs.DB↗

arXiv2025

How to Mine Potentially Popular Items? A Reverse MIPS-based Approach

The $k$-MIPS ($k$ Maximum Inner Product Search) problem has been employed in many fields. Recently, its reverse version, the reverse $k$-MIPS problem, has been proposed. Given an item vector (i.e., query), it retrieves all user vectors such that their $k$-MIPS results contain the item vector. Consider the cardinality of a reverse $k$-MIPS result. A large cardinality means that the item is potentially popular, because it is included in the $k$-MIPS results of many users. This mining is important in recommender systems, market analysis, and new item development. Motivated by this, we formulate a new problem. In this problem, the score of each item is defined as the cardinality of its reverse $k$-MIPS result, and the $N$ items with the highest score are retrieved. A straightforward approach is to compute the scores of all items, but this is clearly prohibitive for large numbers of users and items. We remove this inefficiency issue and propose a fast algorithm for this problem. Because the main bottleneck of the problem is to compute the score of each item, we devise a new upper-bounding technique that is specific to our problem and filters unnecessary score computations. We conduct extensive experiments on real datasets and show the superiority of our algorithm over competitors.

cs.DB↗

arXiv2025

Approximate Reverse $k$-Ranks Queries in High Dimensions

Many objects are represented as high-dimensional vectors nowadays. In this setting, the relevance between two objects (vectors) is usually evaluated by their inner product. Recently, item-centric searches, which search for users relevant to query items, have received attention and find important applications, such as product promotion and market analysis. To support these applications, this paper considers reverse $k$-ranks queries. Given a query vector $\mathbf{q}$, $k$, a set $\mathbf{U}$ of user vectors, and a set $\mathbf{P}$ of item vectors, this query retrieves the $k$ user vectors $\mathbf{u} \in \mathbf{U}$ with the highest $r(\mathbf{q},\mathbf{u},\mathbf{P})$, where $r(\mathbf{q},\mathbf{u},\mathbf{P})$ shows the rank of $\mathbf{q}$ for $\mathbf{u}$ among $\mathbf{P}$. Because efficiently computing the exact answer for this query is difficult in high dimensions, we address the problem of approximate reverse $k$-ranks queries. Informally, given an approximation factor $c$, this problem allows, as an output, a user $\mathbf{u}'$ such that $r(\mathbf{q},\mathbf{u}',\mathbf{P}) > \tau$ but $r(\mathbf{q},\mathbf{u}',\mathbf{P}) \leq c \times \tau$, where $\tau$ is the rank threshold for the exact answer. We propose a new algorithm for solving this problem efficiently. Through theoretical and empirical analyses, we confirm the efficiency and effectiveness of our algorithm.

cs.DB↗

arXiv2024

Efficient Algorithms for Top-k Stabbing Queries on Weighted Interval Data (Full Version)

Intervals have been generated in many applications (e.g., temporal databases), and they are often associated with weights, such as prices. This paper addresses the problem of processing top-k weighted stabbing queries on interval data. Given a set of weighted intervals, a query value, and a result size $k$, this problem finds the $k$ intervals that are stabbed by the query value and have the largest weights. Although this problem finds practical applications (e.g., purchase, vehicle, and cryptocurrency analysis), it has not been well studied. A state-of-the-art algorithm for this problem incurs $O(n\log k)$ time, where $n$ is the number of intervals, so it is not scalable to large $n$. We solve this inefficiency issue and propose an algorithm that runs in $O(\sqrt{n }\log n + k)$ time. Furthermore, we propose an $O(\log n + k)$ algorithm to further accelerate the search efficiency. Experiments on two real large datasets demonstrate that our algorithms are faster than existing algorithms.

cs.DB↗

arXiv2024

Independent Range Sampling on Interval Data (Longer Version)

Many applications require efficient management of large sets of intervals because many objects are associated with intervals (e.g., time and price intervals). In such interval management systems, range search is a primitive operator for retrieving and analysis tasks. As dataset sizes are growing nowadays, range search results are also becoming larger, which may overwhelm users and incur long computation time. Because applications are usually satisfied with a subset of the result set, it is desirable to efficiently obtain only small samples from the result set.We therefore address the problem of independent range sampling on interval data, which outputs $s$ random samples that overlap a given query interval and are independent of the samples of all previous queries. To efficiently solve this problem theoretically and practically, we propose a variant of an interval tree, namely the augmented interval tree (or AIT), and we show that there exists an exact algorithm that needs $O(n \log n)$ space and $O(\log^{2} n + s)$ time, where $n$ is the dataset size. The simple structure of an AIT provides flexible extensions: (i) its time and space complexities respectively become $O(\log^{2} n + s)$ expected and $O(n)$ by bucketing intervals and (ii) it can deal with weighted intervals and outputs $s$ weighted random samples in $O(\log^{2} n+s\log n)$ time. We conduct extensive experiments on real datasets, and the results demonstrate that our algorithms significantly outperform competitors.

cs.DB↗

arXiv2023

Fast Algorithm for Embedded Order Dependency Validation (Extended Version)

Order Dependencies (ODs) have many applications, such as query optimization, data integration, and data cleaning. Although many works addressed the problem of discovering OD (and its variants), they do not consider datasets with missing values, a standard observation in real-world datasets. This paper introduces the novel notion of Embedded ODs (eODs) to deal with missing values. The intuition of eODs is to confirm ODs only on tuples with no missing values on a given embedding (a set of attributes). In this paper, we address the problem of validating a given eOD. If the eOD holds, we return true. Otherwise, we search for an updated embedding such that the updated eOD holds. If such embedding does not exist, we return false. A trivial requirement is to consider an embedding such that the number of ignored tuples is minimized. We show that it is NP-complete to compute such embedding. We therefore propose an efficient heuristic algorithm for validating embedded ODs. We conduct experiments on real-world datasets, and the results confirm the efficiency of our algorithm.

cs.DB↗

arXiv2023

Learned spatial data partitioning

Due to the significant increase in the size of spatial data, it is essential to use distributed parallel processing systems to efficiently analyze spatial data. In this paper, we first study learned spatial data partitioning, which effectively assigns groups of big spatial data to computers based on locations of data by using machine learning techniques. We formalize spatial data partitioning in the context of reinforcement learning and develop a novel deep reinforcement learning algorithm. Our learning algorithm leverages features of spatial data partitioning and prunes ineffective learning processes to find optimal partitions efficiently. Our experimental study, which uses Apache Sedona and real-world spatial data, demonstrates that our method efficiently finds partitions for accelerating distance join queries and reduces the workload run time by up to 59.4%.

cs.DB↗

arXiv2022

Fast Density-Peaks Clustering: Multicore-based Parallelization Approach

Clustering multi-dimensional points is a fundamental task in many fields, and density-based clustering supports many applications as it can discover clusters of arbitrary shapes. This paper addresses the problem of Density-Peaks Clustering (DPC), a recently proposed density-based clustering framework. Although DPC already has many applications, its straightforward implementation incurs a quadratic time computation to the number of points in a given dataset, thereby does not scale to large datasets. To enable DPC on large datasets, we propose efficient algorithms for DPC. Specifically, we propose an exact algorithm, Ex-DPC, and two approximation algorithms, Approx-DPC and S-Approx-DPC. Under a reasonable assumption about a DPC parameter, our algorithms are sub-quadratic, i.e., break the quadratic barrier. Besides, Approx-DPC does not require any additional parameters and can return the same cluster centers as those of Ex-DPC, rendering an accurate clustering result. S-Approx-DPC requires an approximation parameter but can speed up its computational efficiency. We further present that their efficiencies can be accelerated by leveraging multicore processing. We conduct extensive experiments using synthetic and real datasets, and our experimental results demonstrate that our algorithms are efficient, scalable, and accurate.

cs.DB↗

arXiv2022

Learned k-NN Distance Estimation

Big data mining is well known to be an important task for data science, because it can provide useful observations and new knowledge hidden in given large datasets. Proximity-based data analysis is particularly utilized in many real-life applications. In such analysis, the distances to k nearest neighbors are usually employed, thus its main bottleneck is derived from data retrieval. Much efforts have been made to improve the efficiency of these analyses. However, they still incur large costs, because they essentially need many data accesses. To avoid this issue, we propose a machine-learning technique that quickly and accurately estimates the k-NN distances (i.e., distances to the k nearest neighbors) of a given query. We train a fully connected neural network model and utilize pivots to achieve accurate estimation. Our model is designed to have useful advantages: it infers distances to the k-NNs at a time, its inference time is O(1) (no data accesses are incurred), but it keeps high accuracy. Our experimental results and case studies on real datasets demonstrate the efficiency and effectiveness of our solution.

cs.DB↗

arXiv2022

Debiasing Graph Transfer Learning via Item Semantic Clustering for Cross-Domain Recommendations

Deep learning-based recommender systems may lead to over-fitting when lacking training interaction data. This over-fitting significantly degrades recommendation performances. To address this data sparsity problem, cross-domain recommender systems (CDRSs) exploit the data from an auxiliary source domain to facilitate the recommendation on the sparse target domain. Most existing CDRSs rely on overlapping users or items to connect domains and transfer knowledge. However, matching users is an arduous task and may involve privacy issues when data comes from different companies, resulting in a limited application for the above CDRSs. Some studies develop CDRSs that require no overlapping users and items by transferring learned user interaction patterns. However, they ignore the bias in user interaction patterns between domains and hence suffer from an inferior performance compared with single-domain recommender systems. In this paper, based on the above findings, we propose a novel CDRS, namely semantic clustering enhanced debiasing graph neural recommender system (SCDGN), that requires no overlapping users and items and can handle the domain bias. More precisely, SCDGN semantically clusters items from both domains and constructs a cross-domain bipartite graph generated from item clusters and users. Then, the knowledge is transferred via this cross-domain user-cluster graph from the source to the target. Furthermore, we design a debiasing graph convolutional layer for SCDGN to extract unbiased structural knowledge from the cross-domain user-cluster graph. Our Experimental results on three public datasets and a pair of proprietary datasets verify the effectiveness of SCDGN over state-of-the-art models in terms of cross-domain recommendations.

cs.IR↗

arXiv2021

Fast and Exact Outlier Detection in Metric Spaces: A Proximity Graph-based Approach

Distance-based outlier detection is widely adopted in many fields, e.g., data mining and machine learning, because it is unsupervised, can be employed in a generic metric space, and does not have any assumptions of data distributions. Data mining and machine learning applications face a challenge of dealing with large datasets, which requires efficient distance-based outlier detection algorithms. Due to the popularization of computational environments with large memory, it is possible to build a main-memory index and detect outliers based on it, which is a promising solution for fast distance-based outlier detection. Motivated by this observation, we propose a novel approach that exploits a proximity graph. Our approach can employ an arbitrary proximity graph and obtains a significant speed-up against state-of-the-art. However, designing an effective proximity graph raises a challenge, because existing proximity graphs do not consider efficient traversal for distance-based outlier detection. To overcome this challenge, we propose a novel proximity graph, MRPG. Our empirical study using real datasets demonstrates that MRPG detects outliers significantly faster than the state-of-the-art algorithms.

cs.DB↗

arXiv2021

Reverse Maximum Inner Product Search: How to efficiently find users who would like to buy my item?

The MIPS (maximum inner product search), which finds the item with the highest inner product with a given query user, is an essential problem in the recommendation field. It is usual that e-commerce companies face situations where they want to promote and sell new or discounted items. In these situations, we have to consider a question: who are interested in the items and how to find them? This paper answers this question by addressing a new problem called reverse maximum inner product search (reverse MIPS). Given a query vector and two sets of vectors (user vectors and item vectors), the problem of reverse MIPS finds a set of user vectors whose inner product with the query vector is the maximum among the query and item vectors. Although the importance of this problem is clear, its straightforward implementation incurs a computationally expensive cost. We therefore propose Simpfer, a simple, fast, and exact algorithm for reverse MIPS. In an offline phase, Simpfer builds a simple index that maintains a lower-bound of the maximum inner product. By exploiting this index, Simpfer judges whether the query vector can have the maximum inner product or not, for a given user vector, in a constant time. Besides, our index enables filtering user vectors, which cannot have the maximum inner product with the query vector, in a batch. We theoretically demonstrate that Simpfer outperforms baselines employing state-of-the-art MIPS techniques. Furthermore, our extensive experiments on real datasets show that Simpfer is at least two orders magnitude faster than the baselines.

cs.DB↗

arXiv2021

Distributed Spatial-Keyword kNN Monitoring for Location-aware Pub/Sub

Recent applications employ publish/subscribe (Pub/Sub) systems so that publishers can easily receive attentions of customers and subscribers can monitor useful information generated by publishers. Due to the prevalence of smart devices and social networking services, a large number of objects that contain both spatial and keyword information have been generated continuously, and the number of subscribers also continues to increase. This poses a challenge to Pub/Sub systems: they need to continuously extract useful information from massive objects for each subscriber in real time. In this paper, we address the problem of k nearest neighbor monitoring on a spatial-keyword data stream for a large number of subscriptions. To scale well to massive objects and subscriptions, we propose a distributed solution, namely DkM-SKS. Given m workers, DkM-SKS divides a set of subscriptions into m disjoint subsets based on a cost model so that each worker has almost the same kNN-update cost, to maintain load balancing. DkM-SKS allows an arbitrary approach to updating kNN of each subscription, so with a suitable in-memory index, DkM-SKS can accelerate update efficiency by pruning irrelevant subscriptions for a given new object. We conduct experiments on real datasets, and the results demonstrate the efficiency and scalability of DkM-SKS.

cs.DB↗