-
Article
Target link protection against link-prediction-based attacks via artificial bee colony algorithm based on random walk
Link prediction is a network analysis model used to discover missing links or future relationships that may appear, which has been widely used in many real network systems to predict the potential relationship...
-
Article
Contrastive sequential interaction network learning on co-evolving Riemannian spaces
The sequential interaction network usually find itself in a variety of applications, e.g., recommender system. Herein, inferring future interaction is of fundamental importance, and previous efforts are mainly...
-
Article
Introduction to the special issue on recent advances in graph learning: theory, algorithms, applications, and systems
-
Chapter and Conference Paper
Conditional Denoising Diffusion for Sequential Recommendation
Contemporary attention-based sequential recommendations often encounter the oversmoothing problem, which generates indistinguishable representations. Although contrastive learning addresses this problem to a d...
-
Article
Adaptive curvature exploration geometric graph neural network
Graph Neural networks (GNNs) which are powerful and widely applied models are based on the assumption that graph topologies play key roles in the graph representation learning.However, the existing GNN methods...
-
Article
Open AccessFairness in graph-based semi-supervised learning
Machine learning is widely deployed in society, unleashing its power in a wide range of applications owing to the advent of big data. One emerging problem faced by machine learning is the discrimination from d...
-
Chapter and Conference Paper
Hierarchical Encoder-Decoder with Addressable Memory Network for Diagnosis Prediction
Deep learning methods have demonstrated success in diagnosis prediction on Electronic Health Records (EHRs). Early attempts utilize sequential models to encode patient historical records, but they lack the abi...
-
Article
Recent advances in domain-driven data mining
Data mining research has been significantly motivated by and benefited from real-world applications in novel domains. This special issue was proposed and edited to draw attention to domain-driven data mining a...
-
Chapter
Passive Sensing of Affective and Cognitive Functioning in Mood Disorders by Analyzing Keystroke Kinematics and Speech Dynamics
Mood disorders can be difficult to diagnose, evaluate, and treat. They involve affective and cognitive components, both of which need to be closely monitored over the course of the illness. Current methods lik...
-
Chapter and Conference Paper
Concurrent Transformer for Spatial-Temporal Graph Modeling
Previous studies have shown that concurrently extracting spatial and temporal information is a better way to model spatial-temporal data. However, in these studies, the receptive field has been fixed to constr...
-
Chapter
Future Research Directions
Heterogeneous graph (HG) representation has made great progress in recent years, which clearly shows that it is a powerful and promising graph analysis paradigm. However, it is still a young and promising rese...
-
Chapter
The State-of-the-Art of Heterogeneous Graph Representation
In this chapter, we give a comprehensive review of the recent development on heterogeneous graph representation (HGR) methods and techniques. In the method aspect, according to the information used in HGR, exi...
-
Chapter
Introduction
Networks (or graphs) are ubiquitous in the real world, such as social networks, academic networks, biological networks, and so on. Heterogeneous information network (HIN), a.k.a., heterogeneous graph (HG), is ...
-
Chapter
Heterogeneous Graph Representation for Recommendation
With the rapid development of web services, various kinds of useful auxiliary data (a.k.a., side information) become available in recommender systems. To characterize these complex and heterogeneous auxiliary ...
-
Chapter
Heterogeneous Graph Representation for Industry Application
Heterogeneous graph (HG) representation is closely related with the real-world applications, as heterogeneous objects and interactions are ubiquitous in many practical systems. HG representation methods deploy...
-
Chapter
Attribute-Assisted Heterogeneous Graph Representation
The previous heterogeneous graph representation methods mainly focus on preserving the complex interactions and rich semantics into node representation. As a matter of fact, diverse types of nodes in heterogen...
-
Chapter
Emerging Topics of Heterogeneous Graph Representation
Heterogeneous graph (HG) embedding, aiming to project HG into a low-dimensional space, has attracted considerable research attention. We have introduced some kinds of HG embedding methods, and there are also s...
-
Chapter
Graph Neural Networks in Anomaly Detection
Anomaly detection is an important task, which tackles the problem of discovering “different from normal” signals or patterns by analyzing a massive amount of data, thereby identifying and preventing major faul...
-
Chapter
Heterogeneous Graph Representation for Text Mining
Heterogeneous graph representation techniques can be applied in many real-world applications. Even the natural languages that are usually modeled as sequential data can also be constructed as a heterogeneous g...
-
Chapter
Platforms and Practice of Heterogeneous Graph Representation Learning
It is challenging to build a Heterogeneous Graph (HG) representation learning model because HG is heterogeneous, irregular, and sparse. An easy-to-use and friendly framework is important for a beginner to make...
