Search Results for author: Toyotaro Suzumura

Found 39 papers, 12 papers with code

Beyond Spatio-Temporal Representations: Evolving Fourier Transform for Temporal Graphs

no code implementations25 Feb 2024 Anson Bastos, Kuldeep Singh, Abhishek Nadgeri, Manish Singh, Toyotaro Suzumura

Hence, as a reference implementation, we develop a simple neural model induced with EFT for capturing evolving graph spectra.

Revisiting Mobility Modeling with Graph: A Graph Transformer Model for Next Point-of-Interest Recommendation

1 code implementation2 Oct 2023 Xiaohang Xu, Toyotaro Suzumura, Jiawei Yong, Masatoshi Hanai, Chuang Yang, Hiroki Kanezashi, Renhe Jiang, Shintaro Fukushima

Extracting distinct fine-grained features unique to each piece of information is difficult since temporal information often includes spatial information, as users tend to visit nearby POIs.

Is Self-Supervised Pretraining Good for Extrapolation in Molecular Property Prediction?

no code implementations16 Aug 2023 Shun Takashige, Masatoshi Hanai, Toyotaro Suzumura, LiMin Wang, Kenjiro Taura

In material science, the prediction of unobserved values, commonly referred to as extrapolation, is particularly critical for property prediction as it enables researchers to gain insight into materials beyond the limits of available data.

Molecular Property Prediction Property Prediction

Going Beyond Local: Global Graph-Enhanced Personalized News Recommendations

1 code implementation13 Jul 2023 Boming Yang, Dairui Liu, Toyotaro Suzumura, Ruihai Dong, Irene Li

Precisely recommending candidate news articles to users has always been a core challenge for personalized news recommendation systems.

News Recommendation Recommendation Systems

Exploring 360-Degree View of Customers for Lookalike Modeling

no code implementations17 Apr 2023 Md Mostafizur Rahman, Daisuke Kikuta, Satyen Abrol, Yu Hirate, Toyotaro Suzumura, Pablo Loyola, Takuma Ebisu, Manoj Kondapaka

Lookalike models are based on the assumption that user similarity plays an important role towards product selling and enhancing the existing advertising campaigns from a very large user base.

Can Persistent Homology provide an efficient alternative for Evaluation of Knowledge Graph Completion Methods?

1 code implementation30 Jan 2023 Anson Bastos, Kuldeep Singh, Abhishek Nadgeri, Johannes Hoffart, Toyotaro Suzumura, Manish Singh

$\mathcal{KP}$ addresses this by representing the topology of the KG completion methods through the lens of topological data analysis, concretely using persistent homology.

Knowledge Graph Completion Test +1

Learnable Spectral Wavelets on Dynamic Graphs to Capture Global Interactions

no code implementations22 Nov 2022 Anson Bastos, Abhishek Nadgeri, Kuldeep Singh, Toyotaro Suzumura, Manish Singh

Since static methods to learn the graph spectrum would not consider the history of the evolution of the spectrum as the graph evolves with time, we propose a novel approach to learn the graph wavelets to capture this evolving spectra.

Ethereum Fraud Detection with Heterogeneous Graph Neural Networks

no code implementations23 Mar 2022 Hiroki Kanezashi, Toyotaro Suzumura, Xin Liu, Takahiro Hirofuchi

Specifically, we evaluated the model performance of representative homogeneous GNN models which consider single-type nodes and edges and heterogeneous GNN models which support different types of nodes and edges.

Fraud Detection

How Expressive are Transformers in Spectral Domain for Graphs?

1 code implementation23 Jan 2022 Anson Bastos, Abhishek Nadgeri, Kuldeep Singh, Hiroki Kanezashi, Toyotaro Suzumura, Isaiah Onando Mulang'

We further provide a theoretical analysis and prove that the spatial attention mechanism in the transformer cannot effectively capture the desired frequency response, thus, inherently limiting its expressiveness in spectral space.

Graph Representation Learning

Efficient Scaling of Dynamic Graph Neural Networks

no code implementations16 Sep 2021 Venkatesan T. Chakaravarthy, Shivmaran S. Pandian, Saurabh Raje, Yogish Sabharwal, Toyotaro Suzumura, Shashanka Ubaru

We present distributed algorithms for training dynamic Graph Neural Networks (GNN) on large scale graphs spanning multi-node, multi-GPU systems.

Time-Efficient and High-Quality Graph Partitioning for Graph Dynamic Scaling

no code implementations18 Jan 2021 Masatoshi Hanai, Nikos Tziritas, Toyotaro Suzumura, Wentong Cai, Georgios Theodoropoulos

In the case of distributed graph processing, changing the number of the graph partitions while maintaining high partitioning quality imposes serious computational overheads as typically a time-consuming graph partitioning algorithm needs to execute each time repartitioning is required.

graph partitioning Distributed, Parallel, and Cluster Computing Databases Discrete Mathematics Data Structures and Algorithms Social and Information Networks

The Impact of COVID-19 on Flight Networks

no code implementations4 Jun 2020 Toyotaro Suzumura, Hiroki Kanezashi, Mishal Dholakia, Euma Ishii, Sergio Alvarez Napagao, Raquel Pérez-Arnal, Dario Garcia-Gasulla, Toshiaki Murofushi

As COVID-19 transmissions spread worldwide, governments have announced and enforced travel restrictions to prevent further infections.

Exploring Multi-Banking Customer-to-Customer Relations in AML Context with Poincaré Embeddings

no code implementations4 Dec 2019 Lucia Larise Stavarache, Donatas Narbutis, Toyotaro Suzumura, Ray Harishankar, Augustas Žaltauskas

In the recent years money laundering schemes have grown in complexity and speed of realization, affecting financial institutions and millions of customers globally.

Exploring Graph Neural Networks for Stock Market Predictions with Rolling Window Analysis

no code implementations24 Sep 2019 Daiki Matsunaga, Toyotaro Suzumura, Toshihiro Takahashi

For the knowledge graph, we use the Nikkei Value Search data, which is a rich dataset showing mainly supplier relations among Japanese and foreign companies.

Knowledge Graphs

Towards Federated Graph Learning for Collaborative Financial Crimes Detection

no code implementations19 Sep 2019 Toyotaro Suzumura, Yi Zhou, Natahalie Baracaldo, Guangnan Ye, Keith Houck, Ryo Kawahara, Ali Anwar, Lucia Larise Stavarache, Yuji Watanabe, Pablo Loyola, Daniel Klyashtorny, Heiko Ludwig, Kumar Bhaskaran

Advances in technology used in this domain, including machine learning based approaches, can improve upon the effectiveness of financial institutions' existing processes, however, a key challenge that most financial institutions continue to face is that they address financial crimes in isolation without any insight from other firms.

Federated Learning Graph Learning

EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs

8 code implementations26 Feb 2019 Aldo Pareja, Giacomo Domeniconi, Jie Chen, Tengfei Ma, Toyotaro Suzumura, Hiroki Kanezashi, Tim Kaler, Tao B. Schardl, Charles E. Leiserson

Existing approaches typically resort to node embeddings and use a recurrent neural network (RNN, broadly speaking) to regulate the embeddings and learn the temporal dynamics.

Dynamic Link Prediction Edge Classification +3

Adaptive Pattern Matching with Reinforcement Learning for Dynamic Graphs

1 code implementation21 Dec 2018 Hiroki Kanezashi, Toyotaro Suzumura, Dario Garcia-Gasulla, Min-hwan Oh, Satoshi Matsuoka

We propose an incremental graph pattern matching algorithm to deal with time-evolving graph data and also propose an adaptive optimization system based on reinforcement learning to recompute vertices in the incremental process more efficiently.


Scalable Graph Learning for Anti-Money Laundering: A First Look

2 code implementations30 Nov 2018 Mark Weber, Jie Chen, Toyotaro Suzumura, Aldo Pareja, Tengfei Ma, Hiroki Kanezashi, Tim Kaler, Charles E. Leiserson, Tao B. Schardl

Organized crime inflicts human suffering on a genocidal scale: the Mexican drug cartels have murdered 150, 000 people since 2006, upwards of 700, 000 people per year are "exported" in a human trafficking industry enslaving an estimated 40 million people.

Graph Learning

Scalable attribute-aware network embedding with locality

no code implementations17 Apr 2018 Weiyi Liu, Zhining Liu, Toyotaro Suzumura, Guangmin Hu

Here we propose \emph{SANE}, a scalable attribute-aware network embedding algorithm with locality, to learn the joint representation from topology and attributes.

Attribute Network Embedding

Learning Graph Topological Features via GAN

no code implementations11 Sep 2017 Weiyi Liu, Hal Cooper, Min Hwan Oh, Sailung Yeung, Pin-Yu Chen, Toyotaro Suzumura, Lingli Chen

Inspired by the generation power of generative adversarial networks (GANs) in image domains, we introduce a novel hierarchical architecture for learning characteristic topological features from a single arbitrary input graph via GANs.

Principled Multilayer Network Embedding

1 code implementation11 Sep 2017 Weiyi Liu, Pin-Yu Chen, Sailung Yeung, Toyotaro Suzumura, Lingli Chen

Multilayer network analysis has become a vital tool for understanding different relationships and their interactions in a complex system, where each layer in a multilayer network depicts the topological structure of a group of nodes corresponding to a particular relationship.

Social and Information Networks Physics and Society

Full-Network Embedding in a Multimodal Embedding Pipeline

no code implementations WS 2017 Armand Vilalta, Dario Garcia-Gasulla, Ferran Parés, Eduard Ayguadé, Jesus Labarta, Ulises Cortés, Toyotaro Suzumura

In this paper we evaluate the impact of using the Full-Network embedding in this setting, replacing the original image representation in a competitive multimodal embedding generation scheme.

Image Retrieval Network Embedding +1

Building Graph Representations of Deep Vector Embeddings

no code implementations WS 2017 Dario Garcia-Gasulla, Armand Vilalta, Ferran Parés, Jonatan Moreno, Eduard Ayguadé, Jesus Labarta, Ulises Cortés, Toyotaro Suzumura

Patterns stored within pre-trained deep neural networks compose large and powerful descriptive languages that can be used for many different purposes.

Descriptive Graph Embedding

An Out-of-the-box Full-network Embedding for Convolutional Neural Networks

no code implementations ICLR 2018 Dario Garcia-Gasulla, Armand Vilalta, Ferran Parés, Jonatan Moreno, Eduard Ayguadé, Jesus Labarta, Ulises Cortés, Toyotaro Suzumura

Transfer learning for feature extraction can be used to exploit deep representations in contexts where there is very few training data, where there are limited computational resources, or when tuning the hyper-parameters needed for training is not an option.

General Classification Image Classification +2

Fluid Communities: A Competitive, Scalable and Diverse Community Detection Algorithm

2 code implementations27 Mar 2017 Ferran Parés, Dario Garcia-Gasulla, Armand Vilalta, Jonatan Moreno, Eduard Ayguadé, Jesús Labarta, Ulises Cortés, Toyotaro Suzumura

We introduce a community detection algorithm (Fluid Communities) based on the idea of fluids interacting in an environment, expanding and contracting as a result of that interaction.

Data Structures and Algorithms Social and Information Networks Physics and Society

On the Behavior of Convolutional Nets for Feature Extraction

no code implementations3 Mar 2017 Dario Garcia-Gasulla, Ferran Parés, Armand Vilalta, Jonatan Moreno, Eduard Ayguadé, Jesús Labarta, Ulises Cortés, Toyotaro Suzumura

We seek to provide new insights into the behavior of CNN features, particularly the ones from convolutional layers, as this can be relevant for their application to knowledge representation and reasoning.

Descriptive Representation Learning +1

Scalable Parallel Numerical Constraint Solver Using Global Load Balancing

no code implementations18 May 2015 Daisuke Ishii, Kazuki Yoshizoe, Toyotaro Suzumura

We present a scalable parallel solver for numerical constraint satisfaction problems (NCSPs).

Scalable Parallel Numerical CSP Solver

no code implementations6 Nov 2014 Daisuke Ishii, Kazuki Yoshizoe, Toyotaro Suzumura

We present a parallel solver for numerical constraint satisfaction problems (NCSPs) that can scale on a number of cores.

Cannot find the paper you are looking for? You can Submit a new open access paper.