189 citations · 584 across the 63 of their papers we have counts for
19 papers · 1 filter
ContinuouSP: Generative Model for Crystal Structure Prediction with Invariance and Continuity
Yuji Tone, Masatoshi Hanai, Mitsuaki Kawamura +2
The discovery of new materials using crystal structure prediction (CSP) based on generative machine learning models has become a significant research topic in recent years. In this…
GEFM: Graph-Enhanced EEG Foundation Model
Limin Wang, Toyotaro Suzumura, Hiroki Kanezashi
Electroencephalography (EEG) signals provide critical insights for applications in disease diagnosis and healthcare. However, the scarcity of labeled EEG data poses a significant c…
Graph Adapter of EEG Foundation Models for Parameter Efficient Fine Tuning
Toyotaro Suzumura, Hiroki Kanezashi, Shotaro Akahori
In diagnosing neurological disorders from electroencephalography (EEG) data, foundation models such as Transformers have been employed to capture temporal dynamics. Additionally, G…
Beyond Spatio-Temporal Representations: Evolving Fourier Transform for Temporal Graphs
Anson Bastos, Kuldeep Singh, Abhishek Nadgeri +2
We present the Evolving Graph Fourier Transform (EFT), the first invertible spectral transform that captures evolving representations on temporal graphs. We motivate our work by th…
Revisiting Mobility Modeling with Graph: A Graph Transformer Model for Next Point-of-Interest Recommendation
Xiaohang Xu, Toyotaro Suzumura, Jiawei Yong +5
Next Point-of-Interest (POI) recommendation plays a crucial role in urban mobility applications. Recently, POI recommendation models based on Graph Neural Networks (GNN) have been…
On Data Imbalance in Molecular Property Prediction with Pre-training
Limin Wang, Masatoshi Hanai, Toyotaro Suzumura +2
Revealing and analyzing the various properties of materials is an essential and critical issue in the development of materials, including batteries, semiconductors, catalysts, and…
Is Self-Supervised Pretraining Good for Extrapolation in Molecular Property Prediction?
Shun Takashige, Masatoshi Hanai, Toyotaro Suzumura +2
The prediction of material properties plays a crucial role in the development and discovery of materials in diverse applications, such as batteries, semiconductors, catalysts, and…
Can Persistent Homology provide an efficient alternative for Evaluation of Knowledge Graph Completion Methods?
Anson Bastos, Kuldeep Singh, Abhishek Nadgeri +3
In this paper we present a novel method, (), for faster evaluation of Knowledge Graph (KG) completion approaches. Current ranking-bas…
MegaCRN: Meta-Graph Convolutional Recurrent Network for Spatio-Temporal Modeling
Renhe Jiang, Zhaonan Wang, Jiawei Yong +6
Spatio-temporal modeling as a canonical task of multivariate time series forecasting has been a significant research topic in AI community. To address the underlying heterogeneity…
Learnable Spectral Wavelets on Dynamic Graphs to Capture Global Interactions
Anson Bastos, Abhishek Nadgeri, Kuldeep Singh +2
Learning on evolving(dynamic) graphs has caught the attention of researchers as static methods exhibit limited performance in this setting. The existing methods for dynamic graphs…
Spatio-Temporal Meta-Graph Learning for Traffic Forecasting
Renhe Jiang, Zhaonan Wang, Jiawei Yong +6
Traffic forecasting as a canonical task of multivariate time series forecasting has been a significant research topic in AI community. To address the spatio-temporal heterogeneity…
mdx: A Cloud Platform for Supporting Data Science and Cross-Disciplinary Research Collaborations
Toyotaro Suzumura, Akiyoshi Sugiki, Hiroyuki Takizawa +30
The growing amount of data and advances in data science have created a need for a new kind of cloud platform that provides users with flexibility, strong security, and the ability…
Ethereum Fraud Detection with Heterogeneous Graph Neural Networks
Hiroki Kanezashi, Toyotaro Suzumura, Xin Liu +1
While transactions with cryptocurrencies such as Ethereum are becoming more prevalent, fraud and other criminal transactions are not uncommon. Graph analysis algorithms and machine…
How Expressive are Transformers in Spectral Domain for Graphs?
Anson Bastos, Abhishek Nadgeri, Kuldeep Singh +3
The recent works proposing transformer-based models for graphs have proven the inadequacy of Vanilla Transformer for graph representation learning. To understand this inadequacy, t…
Exploring Graph Neural Networks for Stock Market Predictions with Rolling Window Analysis
Daiki Matsunaga, Toyotaro Suzumura, Toshihiro Takahashi
Recently, there has been a surge of interest in the use of machine learning to help aid in the accurate predictions of financial markets. Despite the exciting advances in this cros…
EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphs
Aldo Pareja, Giacomo Domeniconi, Jie Chen +6
Graph representation learning resurges as a trending research subject owing to the widespread use of deep learning for Euclidean data, which inspire various creative designs of neu…
Scalable attribute-aware network embedding with locality
Weiyi Liu, Zhining Liu, Toyotaro Suzumura +1
Adding attributes for nodes to network embedding helps to improve the ability of the learned joint representation to depict features from topology and attributes simultaneously. Re…
Can GAN Learn Topological Features of a Graph?
Weiyi Liu, Pin-Yu Chen, Hal Cooper +3
This paper is first-line research expanding GANs into graph topology analysis. By leveraging the hierarchical connectivity structure of a graph, we have demonstrated that generativ…
An Out-of-the-box Full-network Embedding for Convolutional Neural Networks
Dario Garcia-Gasulla, Armand Vilalta, Ferran Parés +5
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 resour…