Search Results for author:
Found 88 papers, 21 papers with code
Efficient and Interpretable Compressive Text Summarisation with Unsupervised Dual-Agent Reinforcement Learning
Recently, compressive text summarisation offers a balance between the conciseness issue of extractive summarisation and the factual hallucination issue of abstractive summarisation.
Revisiting Generalized p-Laplacian Regularized Framelet GCNs: Convergence, Energy Dynamic and Training with Non-Linear Diffusion
This work presents a comprehensive theoretical analysis of graph p-Laplacian based framelet network (pL-UFG) to establish a solid understanding of its properties.
Diffusion Models for Time Series Applications: A Survey
Diffusion models, a family of generative models based on deep learning, have become increasingly prominent in cutting-edge machine learning research.
Graph Contrastive Learning with Implicit Augmentations
Existing graph contrastive learning methods rely on augmentation techniques based on random perturbations (e. g., randomly adding or dropping edges and nodes).
Generalized Laplacian Regularized Framelet GCNs
This paper introduces a novel Framelet Graph approach based on p-Laplacian GNN.
A Magnetic Framelet-Based Convolutional Neural Network for Directed Graphs
Spectral Graph Convolutional Networks (spectral GCNNs), a powerful tool for analyzing and processing graph data, typically apply frequency filtering via Fourier transform to obtain representations with selective information.
SA-MLP: Distilling Graph Knowledge from GNNs into Structure-Aware MLP
Then, we introduce a novel structure-mixing knowledge distillation strategy to enhance the learning ability of MLPs for structure information.
Generalized energy and gradient flow via graph framelets
In this work, we provide a theoretical understanding of the framelet-based graph neural networks through the perspective of energy gradient flow.
Riemannian accelerated gradient methods via extrapolation
In this paper, we propose a simple acceleration scheme for Riemannian gradient methods by extrapolating iterates on manifolds.
Embedding Graphs on Grassmann Manifold
Learning efficient graph representation is the key to favorably addressing downstream tasks on graphs, such as node or graph property prediction.
Universal Deep GNNs: Rethinking Residual Connection in GNNs from a Path Decomposition Perspective for Preventing the Over-smoothing
The performance of GNNs degrades as they become deeper due to the over-smoothing.
Ranked #7 on
Node Classification
on Squirrel
A Simple Yet Effective SVD-GCN for Directed Graphs
In this paper, we propose a simple yet effective graph neural network for directed graphs (digraph) based on the classic Singular Value Decomposition (SVD), named SVD-GCN.
Differentially private Riemannian optimization
We introduce a framework of differentially private Riemannian optimization by adding noise to the Riemannian gradient on the tangent space.
Riemannian Hamiltonian methods for min-max optimization on manifolds
In this paper, we study the min-max optimization problems on Riemannian manifolds.
OTExtSum: Extractive Text Summarisation with Optimal Transport
Optimal sentence extraction is conceptualised as obtaining an optimal summary that minimises the transportation cost to a given document regarding their semantic distributions.
Exploiting Neighbor Effect: Conv-Agnostic GNNs Framework for Graphs with Heterophily
Moreover, we propose a simple yet effective Conv-Agnostic GNN framework (CAGNNs) to enhance the performance of most GNNs on heterophily datasets by learning the neighbor effect for each node.
Robust Graph Representation Learning for Local Corruption Recovery
The performance of graph representation learning is affected by the quality of graph input.
Riemannian block SPD coupling manifold and its application to optimal transport
In this work, we study the optimal transport (OT) problem between symmetric positive definite (SPD) matrix-valued measures.
Quasi-Framelets: Another Improvement to GraphNeural Networks
This paper aims to provide a novel design of a multiscale framelets convolution for spectral graph neural networks.
Wasserstein Adversarially Regularized Graph Autoencoder
This paper introduces Wasserstein Adversarially Regularized Graph Autoencoder (WARGA), an implicit generative algorithm that directly regularizes the latent distribution of node embedding to a target distribution via the Wasserstein metric.
Graph Denoising with Framelet Regularizer
As graph data collected from the real world is merely noise-free, a practical representation of graphs should be robust to noise.
Generalized Bures-Wasserstein Geometry for Positive Definite Matrices
This paper proposes a generalized Bures-Wasserstein (BW) Riemannian geometry for the manifold of symmetric positive definite matrices.
How Neural Processes Improve Graph Link Prediction
Link prediction is a fundamental problem in graph data analysis.
Neural Ordinary Differential Equation Model for Evolutionary Subspace Clustering and Its Applications
In this paper, we propose a neural ODE model for evolutionary subspace clustering to overcome this limitation and a new objective function with subspace self-expressiveness constraint is introduced.
Differentiable Neural Architecture Search with Morphism-based Transformable Backbone Architectures
It is extended from the existing study on differentiable neural architecture search, and we made the backbone architecture transformable rather than fixed during the training process.
A Discussion On the Validity of Manifold Learning
In this work, we investigate the validity of learning results of some widely used DR and ManL methods through the chart mapping function of a manifold.
On Riemannian Optimization over Positive Definite Matrices with the Bures-Wasserstein Geometry
We build on this to show that the BW metric is a more suitable and robust choice for several Riemannian optimization problems over ill-conditioned SPD matrices.
Graph Decoupling Attention Markov Networks for Semi-supervised Graph Node Classification
In this paper, we consider the label dependency of graph nodes and propose a decoupling attention mechanism to learn both hard and soft attention.
Grassmann Graph Embedding
Geometric deep learning that employs the geometric and topological features of data has attracted increasing attention in deep neural networks.
How Framelets Enhance Graph Neural Networks
The graph neural networks with the proposed framelet convolution and pooling achieve state-of-the-art performance in many node and graph prediction tasks.
CaEGCN: Cross-Attention Fusion based Enhanced Graph Convolutional Network for Clustering
In this paper, we propose a cross-attention based deep clustering framework, named Cross-Attention Fusion based Enhanced Graph Convolutional Network (CaEGCN), which contains four main modules: the cross-attention fusion module which innovatively concatenates the Content Auto-encoder module (CAE) relating to the individual data and Graph Convolutional Auto-encoder module (GAE) relating to the relationship between the data in a layer-by-layer manner, and the self-supervised model that highlights the discriminative information for clustering tasks.
Escape saddle points faster on manifolds via perturbed Riemannian stochastic recursive gradient
In this paper, we propose a variant of Riemannian stochastic recursive gradient method that can achieve second-order convergence guarantee and escape saddle points using simple perturbation.
Adaptive Hierarchical Hyper-gradient Descent
In this study, we investigate learning rate adaption at different levels based on the hyper-gradient descent framework and propose a method that adaptively learns the optimizer parameters by combining multiple levels of learning rates with hierarchical structures.
Riemannian stochastic recursive momentum method for non-convex optimization
We propose a stochastic recursive momentum method for Riemannian non-convex optimization that achieves a near-optimal complexity of $\tilde{\mathcal{O}}(\epsilon^{-3})$ to find $\epsilon$-approximate solution with one sample.
Regularized Flexible Activation Function Combinations for Deep Neural Networks
Based on this, a novel family of flexible activation functions that can replace sigmoid or tanh in LSTM cells are implemented, as well as a new family by combining ReLU and ELUs.
MathNet: Haar-Like Wavelet Multiresolution-Analysis for Graph Representation and Learning
In this paper, we propose a framework for graph neural networks with multiresolution Haar-like wavelets, or MathNet, with interrelated convolution and pooling strategies.
Variance reduction for Riemannian non-convex optimization with batch size adaptation
Variance reduction techniques are popular in accelerating gradient descent and stochastic gradient descent for optimization problems defined on both Euclidean space and Riemannian manifold.
A Bayesian Long Short-Term Memory Model for Value at Risk and Expected Shortfall Joint Forecasting
Value-at-Risk (VaR) and Expected Shortfall (ES) are widely used in the financial sector to measure the market risk and manage the extreme market movement.
On the Trend-corrected Variant of Adaptive Stochastic Optimization Methods
Adam-type optimizers, as a class of adaptive moment estimation methods with the exponential moving average scheme, have been successfully used in many applications of deep learning.
Coupling Matrix Manifolds and Their Applications in Optimal Transport
These geometrical features of CMM have paved the way for developing numerical Riemannian optimization algorithms such as Riemannian gradient descent and Riemannian trust-region algorithms, forming a uniform optimization method for all types of OT problems.
LSTM-Assisted Evolutionary Self-Expressive Subspace Clustering
Massive volumes of high-dimensional data that evolves over time is continuously collected by contemporary information processing systems, which brings up the problem of organizing this data into clusters, i. e. achieve the purpose of dimensional deduction, and meanwhile learning its temporal evolution patterns.
COMBINED FLEXIBLE ACTIVATION FUNCTIONS FOR DEEP NEURAL NETWORKS
Based on this, we develop two novel flexible activation functions that can be implemented in LSTM cells and auto-encoder layers.
Tensor-Train Parameterization for Ultra Dimensionality Reduction
Thus, we propose a tensor-train parameterization for ultra dimensionality reduction (TTPUDR) in which the traditional LPP mapping is tensorized in terms of tensor-trains and the LPP objective is replaced with the Frobenius norm to increase the robustness of the model.
Shared Generative Latent Representation Learning for Multi-view Clustering
Clustering multi-view data has been a fundamental research topic in the computer vision community.
DataLearner: A Data Mining and Knowledge Discovery Tool for Android Smartphones and Tablets
Smartphones have become the ultimate 'personal' computer, yet despite this, general-purpose data-mining and knowledge discovery tools for mobile devices are surprisingly rare.
Manifold Optimization Assisted Gaussian Variational Approximation
Gaussian variational approximation is a popular methodology to approximate posterior distributions in Bayesian inference especially in high dimensional and large data settings.
Sparse Least Squares Low Rank Kernel Machines
A general framework of least squares support vector machine with low rank kernels, referred to as LR-LSSVM, is introduced in this paper.
A Review for Weighted MinHash Algorithms
In this review, we mainly categorize the Weighted MinHash algorithms into quantization-based approaches, "active index"-based ones and others, and show the evolution and inherent connection of the weighted MinHash algorithms, from the integer weighted MinHash algorithms to real-valued weighted MinHash ones (particularly the Consistent Weighted Sampling scheme).
Data Structures and Algorithms
Where-and-When to Look: Deep Siamese Attention Networks for Video-based Person Re-identification
Video-based person re-identification (re-id) is a central application in surveillance systems with significant concern in security.
Deep Co-attention based Comparators For Relative Representation Learning in Person Re-identification
Recent effective methods are developed in a pair-wise similarity learning system to detect a fixed set of features from distinct regions which are mapped to their vector embeddings for the distance measuring.
Tensorial Recurrent Neural Networks for Longitudinal Data Analysis
In this paper, we propose a new variant of tensorial neural networks which directly take tensorial time series data as inputs.
What-and-Where to Match: Deep Spatially Multiplicative Integration Networks for Person Re-identification
To address \emph{what} to match, our deep network emphasizes common local patterns by learning joint representations in a multiplicative way.
Vectorial Dimension Reduction for Tensors Based on Bayesian Inference
Under this expression, the projection base of the model is based on the tensor CandeComp/PARAFAC (CP) decomposition and the number of free parameters in the model only grows linearly with the number of modes rather than exponentially.
Grassmannian Manifold Optimization Assisted Sparse Spectral Clustering
Spectral Clustering is one of pioneered clustering methods in machine learning and pattern recognition field.
Low-Rank-Sparse Subspace Representation for Robust Regression
Learning robust regression model from high-dimensional corrupted data is an essential and difficult problem in many practical applications.
Deep Adaptive Feature Embedding with Local Sample Distributions for Person Re-identification
To this end, a novel objective function is proposed to jointly optimize similarity metric learning, local positive mining and robust deep embedding.
Assessing the Performance of Deep Learning Algorithms for Newsvendor Problem
In the traditional approach to solving this problem, it relies on the probability distribution of the demand.
Localized LRR on Grassmann Manifolds: An Extrinsic View
Subspace data representation has recently become a common practice in many computer vision tasks.
Locality Preserving Projections for Grassmann manifold
Learning on Grassmann manifold has become popular in many computer vision tasks, with the strong capability to extract discriminative information for imagesets and videos.
Tractable Clustering of Data on the Curve Manifold
However the data may actually be functional i. e.\ each data point is a function of some variable such as time and the function is discretely sampled.
Efficient Sparse Subspace Clustering by Nearest Neighbour Filtering
Sparse Subspace Clustering (SSC) has been used extensively for subspace identification tasks due to its theoretical guarantees and relative ease of implementation.
Collaborative Low-Rank Subspace Clustering
In this paper we present Collaborative Low-Rank Subspace Clustering.
Matrix Variate RBM Model with Gaussian Distributions
Restricted Boltzmann Machine (RBM) is a particular type of random neural network models modeling vector data based on the assumption of Bernoulli distribution.
Partial Least Squares Regression on Riemannian Manifolds and Its Application in Classifications
Partial least squares regression (PLSR) has been a popular technique to explore the linear relationship between two datasets.
Low-rank Multi-view Clustering in Third-Order Tensor Space
Multi-view subspace clustering is based on the fact that the multi-view data are generated from a latent subspace.
Laplacian LRR on Product Grassmann Manifolds for Human Activity Clustering in Multi-Camera Video Surveillance
In multi-camera video surveillance, it is challenging to represent videos from different cameras properly and fuse them efficiently for specific applications such as human activity recognition and clustering.
Proximal Riemannian Pursuit for Large-Scale Trace-Norm Minimization
Trace-norm regularization plays an important role in many areas such as machine learning and computer vision.
Neighborhood Preserved Sparse Representation for Robust Classification on Symmetric Positive Definite Matrices
Due to its promising classification performance, sparse representation based classification(SRC) algorithm has attracted great attention in the past few years.
Partial Sum Minimization of Singular Values Representation on Grassmann Manifolds
As a significant subspace clustering method, low rank representation (LRR) has attracted great attention in recent years.
Kernelized LRR on Grassmann Manifolds for Subspace Clustering
The novelty of this paper is to generalize LRR on Euclidean space onto an LRR model on Grassmann manifold in a uniform kernelized LRR framework.
Mixture of Bilateral-Projection Two-dimensional Probabilistic Principal Component Analysis
This paper proposes a mixture of bilateral-projection probabilistic principal component analysis model (mixB2DPPCA) on 2D data.
Block-Diagonal Sparse Representation by Learning a Linear Combination Dictionary for Recognition
In a sparse representation based recognition scheme, it is critical to learn a desired dictionary, aiming both good representational power and discriminative performance.
Low-Rank Representation over the Manifold of Curves
However the data may actually be functional i. e.\ each data point is a function of some variable such as time and the function is discretely sampled.
Matrix Variate RBM and Its Applications
In this paper, a Matrix-Variate Restricted Boltzmann Machine (MVRBM) model is proposed by generalizing the classic RBM to explicitly model matrix data.
Kernel Sparse Subspace Clustering on Symmetric Positive Definite Manifolds
Sparse subspace clustering (SSC), as one of the most successful subspace clustering methods, has achieved notable clustering accuracy in computer vision tasks.
Tensor Sparse and Low-Rank based Submodule Clustering Method for Multi-way Data
A new submodule clustering method via sparse and low-rank representation for multi-way data is proposed in this paper.
Fast Optimization Algorithm on Riemannian Manifolds and Its Application in Low-Rank Representation
The paper addresses the problem of optimizing a class of composite functions on Riemannian manifolds and a new first order optimization algorithm (FOA) with a fast convergence rate is proposed.
l1-norm Penalized Orthogonal Forward Regression
A l1-norm penalized orthogonal forward regression (l1-POFR) algorithm is proposed based on the concept of leaveone- out mean square error (LOOMSE).
Low Rank Representation on Riemannian Manifold of Square Root Densities
In this paper, we present a novel low rank representation (LRR) algorithm for data lying on the manifold of square root densities.
Learning Graph Structure for Multi-Label Image Classification via Clique Generation
Exploiting label dependency for multi-label image classification can significantly improve classification performance.
Segmentation of Subspaces in Sequential Data
We propose Ordered Subspace Clustering (OSC) to segment data drawn from a sequentially ordered union of subspaces.
Kernelized Low Rank Representation on Grassmann Manifolds
One of its successful applications is subspace clustering which means data are clustered according to the subspaces they belong to.
Low Rank Representation on Grassmann Manifolds: An Extrinsic Perspective
Many computer vision algorithms employ subspace models to represent data.
Heterogeneous Tensor Decomposition for Clustering via Manifold Optimization
In contrast to existing techniques, we propose a new clustering algorithm that alternates between different modes of the proposed heterogeneous tensor model.
Scalable Nuclear-norm Minimization by Subspace Pursuit Proximal Riemannian Gradient
Nuclear-norm regularization plays a vital role in many learning tasks, such as low-rank matrix recovery (MR), and low-rank representation (LRR).
Relations among Some Low Rank Subspace Recovery Models
More specifically, we discover that once a solution to one of the models is obtained, we can obtain the solutions to other models in closed-form formulations.
Subspace Clustering for Sequential Data
We propose Ordered Subspace Clustering (OSC) to segment data drawn from a sequentially ordered union of subspaces.
