
GraphBert: Only Attention is Needed for Learning Graph Representations
The dominant graph neural networks (GNNs) overrely on the graph links, ...
read it

IsoNN: Isomorphic Neural Network for Graph Representation Learning and Classification
Deep learning models have achieved huge success in numerous fields, such...
read it

Ripple Walk Training: A Subgraphbased training framework for Large and Deep Graph Neural Network
Graph neural networks (GNNs) have achieved outstanding performance in le...
read it

G5: A Universal GRAPHBERT for GraphtoGraph Transfer and Apocalypse Learning
The recent GRAPHBERT model introduces a new approach to learning graph ...
read it

Get Rid of Suspended Animation Problem: Deep Diffusive Neural Network on Graph SemiSupervised Classification
Existing graph neural networks may suffer from the "suspended animation ...
read it

SEGEN: SampleEnsemble Genetic Evolutional Network Model
Deep learning, a rebranding of deep neural network research works, has a...
read it

Social Network Fusion and Mining: A Survey
Looking from a global perspective, the landscape of online social networ...
read it

GADAM: GeneticEvolutionary ADAM for Deep Neural Network Optimization
Deep neural network learning can be formulated as a nonconvex optimizat...
read it

Spectral Collaborative Filtering
Despite the popularity of Collaborative Filtering (CF), CFbased methods...
read it

A SelfOrganizing Tensor Architecture for MultiView Clustering
In many realworld applications, data are often unlabeled and comprised ...
read it

Gradient Descent based Optimization Algorithms for Deep Learning Models Training
In this paper, we aim at providing an introduction to the gradient desce...
read it

DerivativeFree Global Optimization Algorithms: Population based Methods and Random Search Approaches
In this paper, we will provide an introduction to the derivativefree op...
read it

DerivativeFree Global Optimization Algorithms: Bayesian Method and Lipschitzian Approaches
In this paper, we will provide an introduction to the derivativefree op...
read it

Missing Movie Synergistic Completion across Multiple Isomeric Online Movie Knowledge Libraries
Online knowledge libraries refer to the online data warehouses that syst...
read it

Secrets of the Brain: An Introduction to the Brain Anatomical Structure and Biological Function
In this paper, we will provide an introduction to the brain structure an...
read it

Cognitive Functions of the Brain: Perception, Attention and Memory
This is a followup tutorial article of [17] and [16], in this paper, we...
read it

Graph Neural Lasso for Dynamic Network Regression
In this paper, we will study the dynamic network regression problem, whi...
read it

DEAM: Accumulated Momentum with Discriminative Weight for Stochastic Optimization
Optimization algorithms with momentum, e.g., Nesterov Accelerated Gradie...
read it

Graph Neural Networks for Small Graph and Giant Network Representation Learning: An Overview
Graph neural networks denote a group of neural network models introduced...
read it

BGADAM: Boosting based GeneticEvolutionary ADAM for Convolutional Neural Network Optimization
Among various optimization algorithms, ADAM can achieve outstanding perf...
read it

GRESNET: Graph Residuals for Reviving Deep Graph Neural Nets from Suspended Animation
In this paper, we will investigate the causes of the GNNs' "suspended an...
read it

GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animation
The existing graph neural networks (GNNs) based on the spectral graph co...
read it

Heterogeneous Deep Graph Infomax
Graph representation learning is to learn universal node representations...
read it

CGBERT: Conditional Text Generation with BERT for Generalized Fewshot Intent Detection
In this paper, we formulate a more realistic and difficult problem setup...
read it

Centrality Meets Centroid: A Graphbased Approach for Unsupervised Document Summarization
Unsupervised document summarization has reacquired lots of attention in...
read it
IFM Lab
Our lab focuses on fusing multiple largescale information sources of diverse varieties together, and carrying out synergistic data mining tasks across these fused sources in one unified analytic. Fusing and mining multiple information sources of large volumes and diverse varieties is a fundamental problem in big data studies. We strive to develop general methodologies for information fusion and mining, which will be shown to work well for a diverse set of applications.