no code implementations • 14 May 2024 • Vivek Mohan, Wee Peng Tay, Arindam Basu
This work introduces two novel neural spike detection schemes intended for use in next-generation neuromorphic brain-machine interfaces (iBMIs).
2 code implementations • 26 Apr 2024 • Qiyu Kang, Kai Zhao, Qinxu Ding, Feng Ji, Xuhao Li, Wenfei Liang, Yang song, Wee Peng Tay
We introduce the FRactional-Order graph Neural Dynamical network (FROND), a new continuous graph neural network (GNN) framework.
no code implementations • 22 Apr 2024 • Rui She, Qiyu Kang, Sijie Wang, Wee Peng Tay, Kai Zhao, Yang song, Tianyu Geng, Yi Xu, Diego Navarro Navarro, Andreas Hartmannsgruber
Point cloud registration is a fundamental technique in 3-D computer vision with applications in graphics, autonomous driving, and robotics.
no code implementations • 9 Jan 2024 • Qiyu Kang, Kai Zhao, Yang song, Yihang Xie, Yanan Zhao, Sijie Wang, Rui She, Wee Peng Tay
In this work, we rigorously investigate the robustness of graph neural fractional-order differential equation (FDE) models.
no code implementations • 6 Jan 2024 • Rui She, Sijie Wang, Qiyu Kang, Kai Zhao, Yang song, Wee Peng Tay, Tianyu Geng, Xingchao Jian
We leverage a graph neural partial differential equation (PDE) based on Beltrami flow to obtain high-dimensional features and position embeddings for point clouds.
1 code implementation • 17 Dec 2023 • Sijie Wang, Rui She, Qiyu Kang, Xingchao Jian, Kai Zhao, Yang song, Wee Peng Tay
The utilization of multi-modal sensor data in visual place recognition (VPR) has demonstrated enhanced performance compared to single-modal counterparts.
no code implementations • 15 Dec 2023 • Vivek Mohan, Wee Peng Tay, Arindam Basu
Furthermore, we use accuracy, sensitivity, and false detection rate to understand the effect of compression on downstream iBMI tasks, specifically, spike detection.
no code implementations • 13 Dec 2023 • Feng Ji, Xingchao Jian, Wee Peng Tay
Our signal processing framework provides a comprehensive approach to analyzing and processing signals on graph sequences, even if they are sparse.
no code implementations • 8 Nov 2023 • Rui She, Qiyu Kang, Sijie Wang, Wee Peng Tay, Yong Liang Guan, Diego Navarro Navarro, Andreas Hartmannsgruber
Matching landmark patches from a real-time image captured by an on-vehicle camera with landmark patches in an image database plays an important role in various computer perception tasks for autonomous driving.
1 code implementation • 7 Nov 2023 • Rui She, Qiyu Kang, Sijie Wang, Yuan-Rui Yang, Kai Zhao, Yang song, Wee Peng Tay
For autonomous vehicles (AVs), visual perception techniques based on sensors like cameras play crucial roles in information acquisition and processing.
no code implementations • 25 Oct 2023 • See Hian Lee, Feng Ji, Kelin Xia, Wee Peng Tay
Traditionally, graph neural networks have been trained using a single observed graph.
no code implementations • 23 Oct 2023 • Xingchao Jian, Feng Ji, Wee Peng Tay
The note also contains errata of the previous version of the note.
1 code implementation • NeurIPS 2023 • Kai Zhao, Qiyu Kang, Yang song, Rui She, Sijie Wang, Wee Peng Tay
Graph neural networks (GNNs) are vulnerable to adversarial perturbations, including those that affect both node features and graph topology.
no code implementations • 12 Sep 2023 • Purui Zhang, Xingchao Jian, Feng Ji, Wee Peng Tay, Bihan Wen
We recall the notion of a complexon as the limit of a simplicial complex sequence [1].
no code implementations • 11 Sep 2023 • Xingchao Jian, Feng Ji, Wee Peng Tay
This random graph process converges to the generalized graphon in stretched cut distance.
no code implementations • 14 Aug 2023 • Xingchao Jian, Wee Peng Tay, Yonina C. Eldar
In this paper, we study GGSP signal reconstruction as a kernel ridge regression (KRR) problem.
no code implementations • 16 Jul 2023 • Feng Ji, Wee Peng Tay, Antonio Ortega
In this expository article, we provide a self-contained overview of the notion of convolution embedded in different theories: from the classical Fourier theory to the theory of algebraic signal processing.
no code implementations • 13 Jun 2023 • Wei zhang, Zhenni Wang, Wee Peng Tay
In this paper, we develop a RIS-aided positioning framework to locate a UE in environments where the LOS path may or may not be available.
1 code implementation • 30 May 2023 • Qiyu Kang, Kai Zhao, Yang song, Sijie Wang, Wee Peng Tay
In the graph node embedding problem, embedding spaces can vary significantly for different data types, leading to the need for different GNN model types.
1 code implementation • 26 May 2023 • Kai Zhao, Qiyu Kang, Yang song, Rui She, Sijie Wang, Wee Peng Tay
Graph neural networks (GNNs) have shown promising results across various graph learning tasks, but they often assume homophily, which can result in poor performance on heterophilic graphs.
no code implementations • 11 May 2023 • Feng Ji, Xingchao Jian, Wee Peng Tay, Maosheng Yang
Topological signal processing (TSP) over simplicial complexes typically assumes observations associated with the simplicial complexes are real scalars.
1 code implementation • 29 Apr 2023 • Feng Ji, See Hian Lee, Hanyang Meng, Kai Zhao, Jielong Yang, Wee Peng Tay
We introduce the key notion of label non-uniformity, which is derived from the Wasserstein distance between the softmax distribution of the logits and the uniform distribution.
no code implementations • 7 Apr 2023 • Feng Ji, See Hian Lee, Kai Zhao, Wee Peng Tay, Jielong Yang
In graph neural networks (GNNs), both node features and labels are examples of graph signals, a key notion in graph signal processing (GSP).
2 code implementations • CVPR 2023 • Sijie Wang, Qiyu Kang, Rui She, Wei Wang, Kai Zhao, Yang song, Wee Peng Tay
LiDAR relocalization plays a crucial role in many fields, including robotics, autonomous driving, and computer vision.
no code implementations • 3 Mar 2023 • See Hian Lee, Feng Ji, Wee Peng Tay
However, a graph can have hyperbolic and Euclidean geometries at different regions of the graph.
no code implementations • 2 Mar 2023 • Qiyu Kang, Kai Zhao, Yang song, Sijie Wang, Rui She, Wee Peng Tay
Graph neural networks (GNNs) have achieved success in various inference tasks on graph-structured data.
no code implementations • 24 Feb 2023 • Feng Ji, Xingchao Jian, Wee Peng Tay
In this paper, we propose a framework for graph signal processing using category theory.
no code implementations • 22 Feb 2023 • Feng Ji, Xingchao Jian, Wee Peng Tay
We develop signal processing tools to study the new notion of distributional graph signals.
1 code implementation • 21 Nov 2022 • Sijie Wang, Qiyu Kang, Rui She, Wee Peng Tay, Andreas Hartmannsgruber, Diego Navarro Navarro
Experiments demonstrate that RobustLoc surpasses current state-of-the-art camera pose regression models and achieves robust performance in various environments.
Ranked #1 on Visual Localization on Oxford RobotCar Full
no code implementations • 28 Sep 2022 • Feng Ji, See Hian Lee, Wee Peng Tay
In graph signal processing, one of the most important subjects is the study of filters, i. e., linear transformations that capture relations between graph signals.
1 code implementation • 16 Sep 2022 • Yang song, Qiyu Kang, Sijie Wang, Zhao Kai, Wee Peng Tay
In this work, we explore the robustness properties of graph neural PDEs.
1 code implementation • 24 Jul 2022 • See Hian Lee, Feng Ji, Wee Peng Tay
In this paper, we present Simplicial Graph Attention Network (SGAT), a simplicial complex approach to represent such high-order interactions by placing features from non-target nodes on the simplices.
no code implementations • 9 Jun 2022 • Feng Ji, Yiqi Lu, Wee Peng Tay, Edwin Chong
Graph signal processing is a framework to handle graph structured data.
1 code implementation • 12 May 2022 • Sijie Wang, Qiyu Kang, Rui She, Wee Peng Tay, Diego Navarro Navarro, Andreas Hartmannsgruber
Building facade parsing, which predicts pixel-level labels for building facades, has applications in computer vision perception for autonomous vehicle (AV) driving.
no code implementations • 2 Mar 2022 • Feng Ji, Wee Peng Tay
Graph signal processing (GSP) is a framework to analyze and process graph-structured data.
no code implementations • 2 Dec 2021 • Xingchao Jian, Wee Peng Tay
We consider statistical graph signal processing (GSP) in a generalized framework where each vertex of a graph is associated with an element from a Hilbert space.
no code implementations • 1 Dec 2021 • Wei zhang, Wee Peng Tay
We develop a RIS-aided positioning framework to locate a UE in environments where the LOS path may or may not be available.
2 code implementations • NeurIPS 2021 • Qiyu Kang, Yang song, Qinxu Ding, Wee Peng Tay
By ensuring that the equilibrium points of the ODE solution used as part of SODEF is Lyapunov-stable, the ODE solution for an input with a small perturbation converges to the same solution as the unperturbed input.
no code implementations • 20 Aug 2021 • Feng Ji, Wee Peng Tay, Antonio Ortega
Each graph topology gives rise to a different shift operator.
no code implementations • 29 Mar 2021 • See Hian Lee, Feng Ji, Wee Peng Tay
A heterogeneous graph consists of different vertices and edges types.
no code implementations • 11 Dec 2020 • Feng Ji, Wee Peng Tay
In this paper, we develop a signal processing framework of a network without explicit knowledge of the network topology.
no code implementations • 20 Oct 2020 • Feng Ji, Hui Feng, Hang Sheng, Wee Peng Tay
A continuous-time graph signal can be viewed as a time series of graph signals.
no code implementations • 10 Oct 2020 • Chong Xiao Wang, Wee Peng Tay
We develop an inference privacy framework based on the variational method and include maximum mean discrepancy and domain adaption as techniques to regularize the domain of the sanitized data to ensure its legacy compatibility.
no code implementations • 14 Jul 2020 • Hao Cheng, Joey Tianyi Zhou, Wee Peng Tay, Bihan Wen
Graph Neural Networks (GNN) has demonstrated the superior performance in many challenging applications, including the few-shot learning tasks.
no code implementations • 11 May 2020 • Feng Ji, Wee Peng Tay, Giacomo Kahn
Graph signal processing, like the graph Fourier transform, requires the full graph signal at every vertex of the graph.
no code implementations • 6 Apr 2020 • Feng Ji, Giacomo Kahn, Wee Peng Tay
In this paper, we develop a signal processing framework on simplicial complexes, such that we recover the traditional GSP theory when restricted to signals on graphs.
no code implementations • 30 Nov 2019 • Yang Song, Qiyu Kang, Wee Peng Tay
Though deep learning has been applied successfully in many scenarios, malicious inputs with human-imperceptible perturbations can make it vulnerable in real applications.
no code implementations • 26 Jun 2019 • Qiyu Kang, Wee Peng Tay
In the case where each arm is chosen from an infinite compact set, our strategy achieves $O(n^{2/3}(\log{n})^{1/2})$ regret.
1 code implementation • 25 Jun 2019 • Jielong Yang, Wee Peng Tay
An autoencoder learns the complex relationships between event truths, agent reliabilities and agent observations.
no code implementations • 25 Feb 2019 • Feng Ji, Jielong Yang, Qiang Zhang, Wee Peng Tay
In view of the huge success of convolution neural networks (CNN) for image classification and object recognition, there have been attempts to generalize the method to general graph-structured data.
no code implementations • 27 Jul 2018 • Qiyu Kang, Wee Peng Tay
We develop three task recommendation strategies to determine the number of gold tasks for different task categories, and show that they are order optimal.
no code implementations • 8 Jun 2018 • Jielong Yang, Junshan Wang, Wee Peng Tay
We incorporate knowledge of the agents' social network in our truth discovery framework and develop Laplace variational inference methods to estimate agents' reliabilities, communities, and the event states.
no code implementations • 6 Nov 2017 • Qiyu Kang, Wee Peng Tay
As workers may be unreliable, we propose to perform sequential questioning in which the questions posed to the workers are designed based on previous questions and answers.