Search Results for author:
Found 64 papers, 34 papers with code
BANER: Boundary-Aware LLMs for Few-Shot Named Entity Recognition
In this paper, we propose an approach called Boundary-Aware LLMs for Few-Shot Named Entity Recognition to address these issues.
Question-guided Knowledge Graph Re-scoring and Injection for Knowledge Graph Question Answering
Knowledge graph question answering (KGQA) involves answering natural language questions by leveraging structured information stored in a knowledge graph.
TPN: Transferable Proto-Learning Network towards Few-shot Document-Level Relation Extraction
Few-shot document-level relation extraction suffers from poor performance due to the challenging cross-domain transferability of NOTA (none-of-the-above) relation representation.
Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learning
Moreover, existing methods primarily rely on contrastive learning to maximize mutual information across different graphs, limiting them to multiplex graph redundant scenarios and failing to capture view-unique task-relevant information.
When Heterophily Meets Heterogeneous Graphs: Latent Graphs Guided Unsupervised Representation Learning
Unsupervised heterogeneous graph representation learning (UHGRL) has gained increasing attention due to its significance in handling practical graphs without labels.
Balanced Multi-Relational Graph Clustering
To address the challenge of view imbalance, we propose Balanced Multi-Relational Graph Clustering (BMGC), comprising unsupervised dominant view mining and dual signals guided representation learning.
Simplified PCNet with Robustness
Graph Neural Networks (GNNs) have garnered significant attention for their success in learning the representation of homophilic or heterophilic graphs.
Robust Graph Structure Learning under Heterophily
In this regard, we propose a novel robust graph structure learning method to achieve a high-quality graph from heterophilic data for downstream tasks.
Provable Filter for Real-world Graph Clustering
Motivated by this finding, we construct two graphs that are highly homophilic and heterophilic, respectively.
CDC: A Simple Framework for Complex Data Clustering
In particular, we deploy CDC to graph data of size 111M.
FCDS: Fusing Constituency and Dependency Syntax into Document-Level Relation Extraction
State-of-the-art DocRE methods use a graph structure to connect entities across the document to capture dependency syntax information.
Fine-Grained Bipartite Concept Factorization for Clustering
In this paper we propose a novel concept factorization method that seeks factor matrices using a cross-order positive semi-definite neighbor graph which provides comprehensive and complementary neighbor information of the data.
PC-Conv: Unifying Homophily and Heterophily with Two-fold Filtering
This is attributed to their neglect of homophily in heterophilic graphs, and vice versa.
Upper Bounding Barlow Twins: A Novel Filter for Multi-Relational Clustering
To overcome this drawback, we propose to learn a graph filter motivated by the theoretical analysis of Barlow Twins.
Non-Autoregressive Diffusion-based Temporal Point Processes for Continuous-Time Long-Term Event Prediction
Inspired by the success of denoising diffusion probabilistic models, we propose a diffusion-based non-autoregressive temporal point process model for long-term event prediction in continuous time.
A Prototype-Based Neural Network for Image Anomaly Detection and Localization
This paper proposes ProtoAD, a prototype-based neural network for image anomaly detection and localization.
Intensity-free Convolutional Temporal Point Process: Incorporating Local and Global Event Contexts
Popular convolutional neural networks, which are designated for local context capturing, have never been applied to TPP modelling due to their incapability of modelling in continuous time.
TieFake: Title-Text Similarity and Emotion-Aware Fake News Detection
We also propose a scale-dot product attention mechanism to capture the similarity between title features and textual features.
Spacecraft Anomaly Detection with Attention Temporal Convolution Network
The time series telemetry data generated by on-orbit spacecraft \textcolor{blue}{contains} important information about the status of spacecraft.
Document-level Relation Extraction with Cross-sentence Reasoning Graph
Specifically, a simplified document-level graph is constructed to model the semantic information of all mentions and sentences in a document, and an entity-level graph is designed to explore relations of long-distance cross-sentence entity pairs.
High-order Multi-view Clustering for Generic Data
Firstly, graph filtering is applied to encode structure information, which unifies the processing of attributed graph data and non-graph data in a single framework.
Structure-Preserving Graph Representation Learning
To this end, we propose a novel Structure-Preserving Graph Representation Learning (SPGRL) method, to fully capture the structure information of graphs.
Eliminating Gradient Conflict in Reference-based Line-Art Colorization
To understand the instability in training, we detect the gradient flow of attention and observe gradient conflict among attention branches.
Scalable Multi-view Clustering with Graph Filtering
With the explosive growth of multi-source data, multi-view clustering has attracted great attention in recent years.
Log-based Sparse Nonnegative Matrix Factorization for Data Representation
Nonnegative matrix factorization (NMF) has been widely studied in recent years due to its effectiveness in representing nonnegative data with parts-based representations.
Hyperspectral Image Denoising Using Non-convex Local Low-rank and Sparse Separation with Spatial-Spectral Total Variation Regularization
In this paper, we propose a novel nonconvex approach to robust principal component analysis for HSI denoising, which focuses on simultaneously developing more accurate approximations to both rank and column-wise sparsity for the low-rank and sparse components, respectively.
Multilayer Graph Contrastive Clustering Network
To this end, we propose a generic and effective autoencoder framework for multilayer graph clustering named Multilayer Graph Contrastive Clustering Network (MGCCN).
Multi-view Contrastive Graph Clustering
With the explosive growth of information technology, multi-view graph data have become increasingly prevalent and valuable.
Self-supervised Consensus Representation Learning for Attributed Graph
Self-supervised loss is designed to maximize the agreement of the embeddings of the same node in the topology graph and the feature graph.
Self-paced Principal Component Analysis
Notably, the complexity of each sample is calculated at the beginning of each iteration in order to integrate samples from simple to more complex into training.
Smoothed Multi-View Subspace Clustering
In recent years, multi-view subspace clustering has achieved impressive performance due to the exploitation of complementary imformation across multiple views.
Towards Clustering-friendly Representations: Subspace Clustering via Graph Filtering
The success of subspace clustering depends on the assumption that the data can be separated into different subspaces.
Pseudo-supervised Deep Subspace Clustering
To tackle these problems, we use pairwise similarity to weigh the reconstruction loss to capture local structure information, while a similarity is learned by the self-expression layer.
Structured Graph Learning for Scalable Subspace Clustering: From Single-view to Multi-view
Extensive experiments demonstrate the efficiency and effectiveness of our approach with respect to many state-of-the-art clustering methods.
Kernel Two-Dimensional Ridge Regression for Subspace Clustering
It directly uses 2D data as inputs such that the learning of representations benefits from inherent structures and relationships of the data.
Structured Graph Learning for Clustering and Semi-supervised Classification
Furthermore, most existing graph-based methods conduct clustering and semi-supervised classification on the graph learned from the original data matrix, which doesn't have explicit cluster structure, thus they might not achieve the optimal performance.
On Deep Unsupervised Active Learning
Unsupervised active learning has attracted increasing attention in recent years, where its goal is to select representative samples in an unsupervised setting for human annotating.
Relation-Guided Representation Learning
In this work, we propose a new representation learning method that explicitly models and leverages sample relations, which in turn is used as supervision to guide the representation learning.
Two-Dimensional Semi-Nonnegative Matrix Factorization for Clustering
In particular, projection matrices are sought under the guidance of building new data representations, such that the spatial information is retained and projections are enhanced by the goal of clustering, which helps construct optimal projection directions.
Structure Learning with Similarity Preserving
Leveraging on the underlying low-dimensional structure of data, low-rank and sparse modeling approaches have achieved great success in a wide range of applications.
Multi-view Subspace Clustering via Partition Fusion
Multi-view clustering is an important approach to analyze multi-view data in an unsupervised way.
Large-scale Multi-view Subspace Clustering in Linear Time
A plethora of multi-view subspace clustering (MVSC) methods have been proposed over the past few years.
Multi-graph Fusion for Multi-view Spectral Clustering
Most existing methods don't pay attention to the quality of the graphs and perform graph learning and spectral clustering separately.
Multiple Partitions Aligned Clustering
Most existing multi-view clustering methods explore the heterogeneous information in the space where the data points lie.
Latent Multi-view Semi-Supervised Classification
To explore underlying complementary information from multiple views, in this paper, we propose a novel Latent Multi-view Semi-Supervised Classification (LMSSC) method.
Nonnegative Matrix Factorization with Local Similarity Learning
Existing nonnegative matrix factorization methods focus on learning global structure of the data to construct basis and coefficient matrices, which ignores the local structure that commonly exists among data.
Clustering with Similarity Preserving
A key step of graph-based approach is the similarity graph construction.
RES-PCA: A Scalable Approach to Recovering Low-rank Matrices
This drawback has limited the application of RPCA in solving real world problems.
Low-rank Kernel Learning for Graph-based Clustering
By formulating graph construction and kernel learning in a unified framework, the graph and consensus kernel can be iteratively enhanced by each other.
Similarity Learning via Kernel Preserving Embedding
Data similarity is a key concept in many data-driven applications.
Robust Graph Learning from Noisy Data
The proposed model is able to boost the performance of data clustering, semisupervised classification, and data recovery significantly, primarily due to two key factors: 1) enhanced low-rank recovery by exploiting the graph smoothness assumption, 2) improved graph construction by exploiting clean data recovered by robust PCA.
Self-weighted Multiple Kernel Learning for Graph-based Clustering and Semi-supervised Classification
There are two possible reasons for the failure: (i) most existing MKL methods assume that the optimal kernel is a linear combination of base kernels, which may not hold true; and (ii) some kernel weights are inappropriately assigned due to noises and carelessly designed algorithms.
Two Birds with One Stone: Transforming and Generating Facial Images with Iterative GAN
Generating high fidelity identity-preserving faces with different facial attributes has a wide range of applications.
Unified Spectral Clustering with Optimal Graph
Second, the discrete solution may deviate from the spectral solution since k-means method is well-known as sensitive to the initialization of cluster centers.
Subspace Clustering via Variance Regularized Ridge Regression
Spectral clustering based subspace clustering methods have emerged recently.
Twin Learning for Similarity and Clustering: A Unified Kernel Approach
Thus the learned similarity matrix is often not suitable, let alone optimal, for the subsequent clustering.
Top-N Recommendation on Graphs
To alleviate this problem, this paper proposes a simple recommendation algorithm that fully exploits the similarity information among users and items and intrinsic structural information of the user-item matrix.
A Fast Factorization-based Approach to Robust PCA
Our method can be used as a light-weight, scalable tool for RPCA in the absence of the precise value of the true rank.
Top-N Recommendation with Novel Rank Approximation
Some empirical results demonstrate that it can provide a better approximation to original problems than convex relaxation.
Top-N Recommender System via Matrix Completion
Top-N recommender systems have been investigated widely both in industry and academia.
Robust PCA via Nonconvex Rank Approximation
This approximation to the matrix rank is tighter than the nuclear norm.
Robust Subspace Clustering via Tighter Rank Approximation
For this nonconvex minimization problem, we develop an effective optimization procedure based on a type of augmented Lagrange multipliers (ALM) method.
Robust Subspace Clustering via Smoothed Rank Approximation
However, for many real-world applications, nuclear norm approximation to the rank function can only produce a result far from the optimum.
LogDet Rank Minimization with Application to Subspace Clustering
Most of the recent studies use the nuclear norm as a convex surrogate of the rank operator.
