1 code implementation • 14 Apr 2024 • Tai Hasegawa, Sukwon Yun, Xin Liu, Yin Jun Phua, Tsuyoshi Murata
Leveraging these modified representations, DEGNN subsequently addresses downstream tasks, ensuring robustness against noise present in both edges and node features of real-world graphs.
no code implementations • 4 Apr 2024 • Quentin Jodelet, Xin Liu, Yin Jun Phua, Tsuyoshi Murata
Exemplar-Free Class Incremental Learning is a highly challenging setting where replay memory is unavailable.
no code implementations • 30 Jun 2023 • Quentin Jodelet, Xin Liu, Yin Jun Phua, Tsuyoshi Murata
Experiments on the competitive benchmarks CIFAR100, ImageNet-Subset, and ImageNet demonstrate how this new approach can be used to further improve the performance of state-of-the-art methods for class-incremental learning on large scale datasets.
1 code implementation • CAAI Transactions on Intelligence Technology 2023 • Sunil Kumar Maurya, Xin Liu, Tsuyoshi Murata
Graphs help to define the relationships between entities in the data.
Ranked #1 on Node Classification on twitch-gamers
1 code implementation • CIKM 2022 • Sunil Kumar Maurya, Xin Liu, Tsuyoshi Murata
With extensive experiments, we show that our proposed model outperforms the state-of-the-art GNN models with remarkable improvements up to 27. 8%.
1 code implementation • 30 Jun 2022 • Tsuyoshi Murata, Naveed Afzal
Graph convolution is a recent scalable method for performing deep feature learning on attributed graphs by aggregating local node information over multiple layers.
1 code implementation • 11 Dec 2021 • Nuttapong Chairatanakul, Hoang NT, Xin Liu, Tsuyoshi Murata
Different from the popular recurrent modeling approach, we propose a new solution named LeapRec to the temporal dynamic problem by using trajectory-based meta-learning to model time dependencies.
1 code implementation • 12 Nov 2021 • Sunil Kumar Maurya, Xin Liu, Tsuyoshi Murata
In this work, we decouple the node feature aggregation step and depth of graph neural network, and empirically analyze how different aggregated features play a role in prediction performance.
no code implementations • journal 2021 • Zarina Rakhimberdina, Quentin Jodelet, Xin Liu, Tsuyoshi Murata
With the advent of brain imaging techniques and machine learning tools, much effort has been devoted to building computational models to capture the encoding of visual information in the human brain.
1 code implementation • Findings (EMNLP) 2021 • Nuttapong Chairatanakul, Noppayut Sriwatanasakdi, Nontawat Charoenphakdee, Xin Liu, Tsuyoshi Murata
To address this challenge, we propose dictionary-based heterogeneous graph neural network (DHGNet) that effectively handles the heterogeneity of DHG by two-step aggregations, which are word-level and language-level aggregations.
1 code implementation • 17 May 2021 • Sunil Kumar Maurya, Xin Liu, Tsuyoshi Murata
Combining these techniques, we present a simple and shallow model, Feature Selection Graph Neural Network (FSGNN), and show empirically that the proposed model outperforms other state of the art GNN models and achieves up to 64% improvements in accuracy on node classification tasks.
Ranked #2 on Node Classification on Cornell
no code implementations • 23 Mar 2021 • Quentin Jodelet, Xin Liu, Tsuyoshi Murata
When incrementally trained on new classes, deep neural networks are subject to catastrophic forgetting which leads to an extreme deterioration of their performance on the old classes while learning the new ones.
no code implementations • 1 Jan 2021 • Hoang NT, Takanori Maehara, Tsuyoshi Murata
We study Graph Convolutional Networks (GCN) from the graph signal processing viewpoint by addressing a difference between learning graph filters with fully-connected weights versus trainable polynomial coefficients.
1 code implementation • 22 Nov 2020 • Hoang NT, Takanori Maehara, Tsuyoshi Murata
We study Graph Convolutional Networks (GCN) from the graph signal processing viewpoint by addressing a difference between learning graph filters with fully connected weights versus trainable polynomial coefficients.
1 code implementation • 22 Jul 2020 • Kaushalya Madhawa, Tsuyoshi Murata
In this paper, we propose MetAL, an AL approach that selects unlabeled instances that directly improve the future performance of a classification model.
2 code implementations • 9 Jul 2020 • Hibiki Taguchi, Xin Liu, Tsuyoshi Murata
Notably, our approach does not increase the computational complexity of GCN and it is consistent with GCN when the features are complete.
no code implementations • ICLR Workshop LLD 2019 • Hoang NT, Choong Jun Jin, Tsuyoshi Murata
We study the robustness to symmetric label noise of GNNs training procedures.
1 code implementation • 19 Apr 2018 • Kaushalya Madhawa, Tsuyoshi Murata
We formulate this problem as an exploration-exploitation problem and propose a novel nonparametric multi-arm bandit (MAB) algorithm for identifying which nodes to be queried.