Relations in most of the traditional knowledge graphs (KGs) only reflect static and factual connections, but fail to represent the dynamic activities and state changes about entities.
Specifically, we design (1) Head-Tail Detector based on the multi-head self-attention mechanism and bi-affine classifier to detect boundary tokens, and (2) Token Interaction Tagger based on traditional sequence labeling approaches to characterize the internal token connection within the boundary.
Graph neural networks (GNNs) have emerged as a series of competent graph learning methods for diverse real-world scenarios, ranging from daily applications like recommendation systems and question answering to cutting-edge technologies such as drug discovery in life sciences and n-body simulation in astrophysics.
Graph Neural Networks (GNNs) have achieved tremendous success in a variety of real-world applications by relying on the fixed graph data as input.
Bundle recommendation is an emerging research direction in the recommender system with the focus on recommending customized bundles of items for users.
Disinformation refers to false information deliberately spread to influence the general public, and the negative impact of disinformation on society can be observed for numerous issues, such as political agendas and manipulating financial markets.
To counter the data noise and data scarcity issues in deep graph learning (DGL), increasing graph data augmentation research has been conducted lately.
Contrastive learning is an effective unsupervised method in graph representation learning.
We also evaluate FTROJAN against state-of-the-art defenses as well as several adaptive defenses that are designed on the frequency domain.
We argue that the community information should be considered to identify node pairs in the same communities, where the nodes insides are semantically similar.
Active learning theories and methods have been extensively studied in classical statistical learning settings.
Inspired by total correlation in information theory, we propose the Information-Theoretic Variational Graph Auto-Encoder (InfoVGAE) that learns to project both users and content items (e. g., posts that represent user views) into an appropriate disentangled latent space.
To address these challenges, we propose a novel Graph Multi-View Prototypical (Graph-MVP) framework to extract node embeddings on multiplex graphs.
Extractive text summarization aims at extracting the most representative sentences from a given document as its summary.
Grounding events into a precise timeline is important for natural language understanding but has received limited attention in recent work.
Algorithmic fairness is becoming increasingly important in data mining and machine learning, and one of the most fundamental notions is group fairness.
Despite the prevalence of hypergraphs in a variety of high-impact applications, there are relatively few works on hypergraph representation learning, most of which primarily focus on hyperlink prediction, often restricted to the transductive learning setting.
Generally speaking, the vast majority of the existing works aim to answer the following question, that is, given a graph, what is the best way to mine it?
Network anomaly detection aims to find network elements (e. g., nodes, edges, subgraphs) with significantly different behaviors from the vast majority.
To address the above-mentioned problems, we propose a novel framework, called High-order Deep Multiplex Infomax (HDMI), for learning node embedding on multiplex networks in a self-supervised way.
We propose a novel model called Network of Tensor Time Series, which is comprised of two modules, including Tensor Graph Convolutional Network (TGCN) and Tensor Recurrent Neural Network (TRNN).
In detail, we develop KompaRe, the first of its kind prototype system that provides comparative reasoning capability over large knowledge graphs.
In this paper, we develop a fairness-aware agnostic federated learning framework (AgnosticFair) to deal with the challenge of unknown testing distribution.
The advisor-advisee relationship represents direct knowledge heritage, and such relationship may not be readily available from academic libraries and search engines.
By democratizing the tools required to study network robustness, our goal is to assist researchers and practitioners in analyzing their own networks; and facilitate the development of new research in the field.
More significantly, the degree of the sparsity is steerable such that only exact k well-fitting samples with least reconstruction errors are activated during the optimization, while the residual samples, i. e., the extreme noised ones are eliminated for the global robustness.
A recent trend of fair machine learning is to define fairness as causality-based notions which concern the causal connection between protected attributes and decisions.
A suite of visualizations is designed to illustrate the dynamics of city segmentation and the corresponding interactions are added to support the exploration of the segmentation patterns over time.
In this paper, we studied the association between the change of structural brain volumes to the potential development of Alzheimer's disease (AD).
The algorithm is based on a novel idea of random path, and an extended method is also presented, to enhance the structural similarity when two vertices are completely disconnected.
Social and Information Networks
Understanding the dynamic mechanisms that drive the high-impact scientific work (e. g., research papers, patents) is a long-debated research topic and has many important implications, ranging from personal career development and recruitment search, to the jurisdiction of research resources.
In this paper, we propose a scalable, provable structured low-rank matrix factorization method to recover low-rank and sparse matrices from missing and grossly corrupted data, i. e., robust matrix completion (RMC) problems, or incomplete and grossly corrupted measurements, i. e., compressive principal component pursuit (CPCP) problems.
This survey aims to provide a general, comprehensive, and structured overview of the state-of-the-art methods for anomaly detection in data represented as graphs.
Social and Information Networks Cryptography and Security
Community Question Answering (CQA) websites have become valuable repositories which host a massive volume of human knowledge.
In this paper, we consider a generic setting where we aim to diversify the top-k ranking list based on an arbitrary relevance function and an arbitrary similarity function among all the examples.