arXiv subjects

Makoto Onizuka

Publications and source records attributed to Makoto Onizuka.

At least 37 records · Page 2Linked to original sources

arXiv2023

A Simple and Scalable Graph Neural Network for Large Directed Graphs

Node classification is one of the hottest tasks in graph analysis. Though existing studies have explored various node representations in directed and undirected graphs, they have overlooked the distinctions of their capabilities to capture the information of graphs. To tackle the limitation, we investigate various combinations of node representations (aggregated features vs. adjacency lists) and edge direction awareness within an input graph (directed vs. undirected). We address the first empirical study to benchmark the performance of various GNNs that use either combination of node representations and edge direction awareness. Our experiments demonstrate that no single combination stably achieves state-of-the-art results across datasets, which indicates that we need to select appropriate combinations depending on the dataset characteristics. In response, we propose a simple yet holistic classification method A2DUG which leverages all combinations of node representations in directed and undirected graphs. We demonstrate that A2DUG stably performs well on various datasets and improves the accuracy up to 11.29 compared with the state-of-the-art methods. To spur the development of new methods, we publicly release our complete codebase under the MIT license.

cs.LG↗

arXiv2023

BClean: A Bayesian Data Cleaning System

There is a considerable body of work on data cleaning which employs various principles to rectify erroneous data and transform a dirty dataset into a cleaner one. One of prevalent approaches is probabilistic methods, including Bayesian methods. However, existing probabilistic methods often assume a simplistic distribution (e.g., Gaussian distribution), which is frequently underfitted in practice, or they necessitate experts to provide a complex prior distribution (e.g., via a programming language). This requirement is both labor-intensive and costly, rendering these methods less suitable for real-world applications. In this paper, we propose BClean, a Bayesian Cleaning system that features automatic Bayesian network construction and user interaction. We recast the data cleaning problem as a Bayesian inference that fully exploits the relationships between attributes in the observed dataset and any prior information provided by users. To this end, we present an automatic Bayesian network construction method that extends a structure learning-based functional dependency discovery method with similarity functions to capture the relationships between attributes. Furthermore, our system allows users to modify the generated Bayesian network in order to specify prior information or correct inaccuracies identified by the automatic generation process. We also design an effective scoring model (called the compensative scoring model) necessary for the Bayesian inference. To enhance the efficiency of data cleaning, we propose several approximation strategies for the Bayesian inference, including graph partitioning, domain pruning, and pre-detection. By evaluating on both real-world and synthetic datasets, we demonstrate that BClean is capable of achieving an F-measure of up to 0.9 in data cleaning, outperforming existing Bayesian methods by 2% and other data cleaning methods by 15%.

cs.AI↗

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↗

arXiv2023

GuP: Fast Subgraph Matching by Guard-based Pruning

Subgraph matching, which finds subgraphs isomorphic to a query, is the key to information retrieval from data represented as a graph. To avoid redundant exploration in the data, existing methods restrict the search space by extracting candidate vertices and candidate edges that may constitute isomorphic subgraphs. However, it still requires expensive computation because candidate vertices induce many subgraphs that are not isomorphic to the query. In this paper, we propose GuP, a subgraph matching algorithm with pruning based on guards. Guards are a pattern of intermediate search states that never find isomorphic subgraphs. GuP attaches a guard on each candidate vertex and edge and filters out them adaptively to the search state. The experimental results showed that GuP can efficiently solve various queries, including those that the state-of-the-art methods could not solve in practical time.

cs.DB↗

arXiv2023

Scardina: Scalable Join Cardinality Estimation by Multiple Density Estimators

In recent years, machine learning-based cardinality estimation methods are replacing traditional methods. This change is expected to contribute to one of the most important applications of cardinality estimation, the query optimizer, to speed up query processing. However, none of the existing methods do not precisely estimate cardinalities when relational schemas consist of many tables with strong correlations between tables/attributes. This paper describes that multiple density estimators can be combined to effectively target the cardinality estimation of data with large and complex schemas having strong correlations. We propose Scardina, a new join cardinality estimation method using multiple partitioned models based on the schema structure.

cs.DB↗

arXiv2023

NoSQL Schema Design for Time-Dependent Workloads

In this paper, we propose a schema optimization method for time-dependent workloads for NoSQL databases. In our proposed method, we migrate schema according to changing workloads, and the estimated cost of execution and migration are formulated and minimized as a single integer linear programming problem. Furthermore, we propose a method to reduce the number of optimization candidates by iterating over the time dimension abstraction and optimizing the workload while updating constraints.

cs.DB↗

arXiv2023

GenCAT: Generating Attributed Graphs with Controlled Relationships between Classes, Attributes, and Topology

Generating large synthetic attributed graphs with node labels is an important task to support various experimental studies for graph analysis methods. Existing graph generators fail to simultaneously simulate the relationships between labels, attributes, and topology which real-world graphs exhibit. Motivated by this limitation, we propose GenCAT, an attributed graph generator for controlling those relationships, which has the following advantages. (i) GenCAT generates graphs with user-specified node degrees and flexibly controls the relationship between nodes and labels by incorporating the connection proportion for each node to classes. (ii) Generated attribute values follow user-specified distributions, and users can flexibly control the correlation between the attributes and labels. (iii) Graph generation scales linearly to the number of edges. GenCAT is the first generator to support all three of these practical features. Through extensive experiments, we demonstrate that GenCAT can efficiently generate high-quality complex attributed graphs with user-controlled relationships between labels, attributes, and topology.

cs.SI↗

arXiv2022

Beyond Real-world Benchmark Datasets: An Empirical Study of Node Classification with GNNs

Graph Neural Networks (GNNs) have achieved great success on a node classification task. Despite the broad interest in developing and evaluating GNNs, they have been assessed with limited benchmark datasets. As a result, the existing evaluation of GNNs lacks fine-grained analysis from various characteristics of graphs. Motivated by this, we conduct extensive experiments with a synthetic graph generator that can generate graphs having controlled characteristics for fine-grained analysis. Our empirical studies clarify the strengths and weaknesses of GNNs from four major characteristics of real-world graphs with class labels of nodes, i.e., 1) class size distributions (balanced vs. imbalanced), 2) edge connection proportions between classes (homophilic vs. heterophilic), 3) attribute values (biased vs. random), and 4) graph sizes (small vs. large). In addition, to foster future research on GNNs, we publicly release our codebase that allows users to evaluate various GNNs with various graphs. We hope this work offers interesting insights for future research.

cs.LG↗

arXiv2022

GNN Transformation Framework for Improving Efficiency and Scalability

We propose a framework that automatically transforms non-scalable GNNs into precomputation-based GNNs which are efficient and scalable for large-scale graphs. The advantages of our framework are two-fold; 1) it transforms various non-scalable GNNs to scale well to large-scale graphs by separating local feature aggregation from weight learning in their graph convolution, 2) it efficiently executes precomputation on GPU for large-scale graphs by decomposing their edges into small disjoint and balanced sets. Through extensive experiments with large-scale graphs, we demonstrate that the transformed GNNs run faster in training time than existing GNNs while achieving competitive accuracy to the state-of-the-art GNNs. Consequently, our transformation framework provides simple and efficient baselines for future research on scalable GNNs.

cs.LG↗

arXiv2022

Scaling Private Deep Learning with Low-Rank and Sparse Gradients

Applying Differentially Private Stochastic Gradient Descent (DPSGD) to training modern, large-scale neural networks such as transformer-based models is a challenging task, as the magnitude of noise added to the gradients at each iteration scales with model dimension, hindering the learning capability significantly. We propose a unified framework, $\textsf{LSG}$, that fully exploits the low-rank and sparse structure of neural networks to reduce the dimension of gradient updates, and hence alleviate the negative impacts of DPSGD. The gradient updates are first approximated with a pair of low-rank matrices. Then, a novel strategy is utilized to sparsify the gradients, resulting in low-dimensional, less noisy updates that are yet capable of retaining the performance of neural networks. Empirical evaluation on natural language processing and computer vision tasks shows that our method outperforms other state-of-the-art baselines.

cs.LG↗

arXiv2022

An Empirical Study of Personalized Federated Learning

Federated learning is a distributed machine learning approach in which a single server and multiple clients collaboratively build machine learning models without sharing datasets on clients. A challenging issue of federated learning is data heterogeneity (i.e., data distributions may differ across clients). To cope with this issue, numerous federated learning methods aim at personalized federated learning and build optimized models for clients. Whereas existing studies empirically evaluated their own methods, the experimental settings (e.g., comparison methods, datasets, and client setting) in these studies differ from each other, and it is unclear which personalized federate learning method achieves the best performance and how much progress can be made by using these methods instead of standard (i.e., non-personalized) federated learning. In this paper, we benchmark the performance of existing personalized federated learning through comprehensive experiments to evaluate the characteristics of each method. Our experimental study shows that (1) there are no champion methods, (2) large data heterogeneity often leads to high accurate predictions, and (3) standard federated learning methods (e.g. FedAvg) with fine-tuning often outperform personalized federated learning methods. We open our benchmark tool FedBench for researchers to conduct experimental studies with various experimental settings.

cs.LG↗

arXiv2022

Predicting Parking Lot Availability by Graph-to-Sequence Model: A Case Study with SmartSantander

Nowadays, so as to improve services and urban areas livability, multiple smart city initiatives are being carried out throughout the world. SmartSantander is a smart city project in Santander, Spain, which has relied on wireless sensor network technologies to deploy heterogeneous sensors within the city to measure multiple parameters, including outdoor parking information. In this paper, we study the prediction of parking lot availability using historical data from more than 300 outdoor parking sensors with SmartSantander. We design a graph-to-sequence model to capture the periodical fluctuation and geographical proximity of parking lots. For developing and evaluating our model, we use a 3-year dataset of parking lot availability in the city of Santander. Our model achieves a high accuracy compared with existing sequence-to-sequence models, which is accurate enough to provide a parking information service in the city. We apply our model to a smartphone application to be widely used by citizens and tourists.

cs.LG↗

arXiv2022

Journey of Migrating Millions of Queries on The Cloud

Treasure Data is processing millions of distributed SQL queries every day on the cloud. Upgrading the query engine service at this scale is challenging because we need to migrate all of the production queries of the customers to a new version while preserving the correctness and performance of the data processing pipelines. To ensure the quality of the query engines, we utilize our query logs to build customer-specific benchmarks and replay these queries with real customer data in a secure pre-production environment. To simulate millions of queries, we need effective minimization of test query sets and better reporting of the simulation results to proactively find incompatible changes and performance regression of the new version. This paper describes the overall design of our system and shares various challenges in maintaining the quality of the query engine service on the cloud.

cs.DB↗

arXiv2022

Similarity Search on Computational Notebooks

Computational notebook software such as Jupyter Notebook is popular for data science tasks. Numerous computational notebooks are available on the Web and reusable; however, searching for computational notebooks manually is a tedious task, and so far, there are no tools to search for computational notebooks effectively and efficiently. In this paper, we propose a similarity search on computational notebooks and develop a new framework for the similarity search. Given contents (i.e., source codes, tabular data, libraries, and outputs formats) in computational notebooks as a query, the similarity search problem aims to find top-k computational notebooks with the most similar contents. We define two similarity measures; set-based and graph-based similarities. Set-based similarity handles each content independently, while graph-based similarity captures the relationships between contents. Our framework can effectively prune the candidates of computational notebooks that should not be in the top-k results. Furthermore, we develop optimization techniques such as caching and indexing to accelerate the search. Experiments using Kaggle notebooks show that our method, in particular graph-based similarity, can achieve high accuracy and high efficiency.

cs.IR↗

arXiv2021

Language-aware Indexing for Conjunctive Path Queries

Conjunctive path queries (CPQ) are one of the most frequently used queries for complex graph analysis. However, current graph indexes are not tailored to fully support the power of query languages to express CPQs. Consequently, current methods do not take advantage of significant pruning opportunities during \cpq{} evaluation, resulting in poor query processing performance. We propose the CPQ-aware path index CPQx, the first path index tailored to the expressivity of CPQ. CPQx is built on the partition of the set of source-target vertex pairs of paths in a graph based on the structural notion of path-bisimulation. Path-bisimulation is an equivalence relation on paths such that each partition block induced by the relation consists of paths in the graph indistinguishable with respect to CPQs. This language-aware partitioning of the graph can significantly reduce the cost of query evaluation. We present methods to support the full index life cycle: index construction, maintenance, and query processing with our index. We also develop interest-aware CPQx to reduce index size and index construction overhead while accelerating query evaluation for queries of interest. We demonstrate through extensive experiments on 14 real graphs that our methods accelerate query processing by up to multiple orders of magnitude over the state-of-the-art methods, with smaller index sizes. Our complete C++ codebase is available as open source for further research.

cs.DB↗

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

FedMe: Federated Learning via Model Exchange

Federated learning is a distributed machine learning method in which a single server and multiple clients collaboratively build machine learning models without sharing datasets on clients. Numerous methods have been proposed to cope with the data heterogeneity issue in federated learning. Existing solutions require a model architecture tuned by the central server, yet a major technical challenge is that it is difficult to tune the model architecture due to the absence of local data on the central server. In this paper, we propose Federated learning via Model exchange (FedMe), which personalizes models with automatic model architecture tuning during the learning process. The novelty of FedMe lies in its learning process: clients exchange their models for model architecture tuning and model training. First, to optimize the model architectures for local data, clients tune their own personalized models by comparing to exchanged models and picking the one that yields the best performance. Second, clients train both personalized models and exchanged models by using deep mutual learning, in spite of different model architectures across the clients. We perform experiments on three real datasets and show that FedMe outperforms state-of-the-art federated learning methods while tuning model architectures automatically.

cs.LG↗

arXiv2021

Monotonic Cardinality Estimation of Similarity Selection: A Deep Learning Approach

Due to the outstanding capability of capturing underlying data distributions, deep learning techniques have been recently utilized for a series of traditional database problems. In this paper, we investigate the possibilities of utilizing deep learning for cardinality estimation of similarity selection. Answering this problem accurately and efficiently is essential to many data management applications, especially for query optimization. Moreover, in some applications the estimated cardinality is supposed to be consistent and interpretable. Hence a monotonic estimation w.r.t. the query threshold is preferred. We propose a novel and generic method that can be applied to any data type and distance function. Our method consists of a feature extraction model and a regression model. The feature extraction model transforms original data and threshold to a Hamming space, in which a deep learning-based regression model is utilized to exploit the incremental property of cardinality w.r.t. the threshold for both accuracy and monotonicity. We develop a training strategy tailored to our model as well as techniques for fast estimation. We also discuss how to handle updates. We demonstrate the accuracy and the efficiency of our method through experiments, and show how it improves the performance of a query optimizer.

cs.DB↗