scholarly journals Popularity Prediction of Online Contents via Cascade Graph and Temporal Information

Axioms ◽  
2021 ◽  
Vol 10 (3) ◽  
pp. 159
Author(s):  
Yingdan Shang ◽  
Bin Zhou ◽  
Ye Wang ◽  
Aiping Li ◽  
Kai Chen ◽  
...  
Keyword(s):  
Diffusion Process ◽  
Temporal Information ◽  
Graph Representation ◽  
Temporal Features ◽  
Importance Coefficient ◽  
Pooling Strategies ◽  
Content Recommendation ◽  
Popularity Prediction ◽  
Graph Neural Networks ◽  
Time Information

Predicting the popularity of online content is an important task for content recommendation, social influence prediction and so on. Recent deep learning models generally utilize graph neural networks to model the complex relationship between information cascade graph and future popularity, and have shown better prediction results compared with traditional methods. However, existing models adopt simple graph pooling strategies, e.g., summation or average, which prone to generate inefficient cascade graph representation and lead to unsatisfactory prediction results. Meanwhile, they often overlook the temporal information in the diffusion process which has been proved to be a salient predictor for popularity prediction. To focus attention on the important users and exclude noises caused by other less relevant users when generating cascade graph representation, we learn the importance coefficient of users and adopt sample mechanism in graph pooling process. In order to capture the temporal features in the diffusion process, we incorporate the inter-infection duration time information into our model by using LSTM neural network. The results show that temporal information rather than cascade graph information is a better predictor for popularity. The experimental results on real datasets show that our model significantly improves the prediction accuracy compared with other state-of-the-art methods.

scholarly journals TSI-GNN: Extending Graph Neural Networks to Handle Missing Data in Temporal Settings

2021 ◽  
Vol 4 ◽  
Author(s):  
David Gordon ◽  
Panayiotis Petousis ◽  
Henry Zheng ◽  
Davina Zamanzadeh ◽  
Alex A.T. Bui
Keyword(s):  
Neural Networks ◽  
Missing Data ◽  
Bipartite Graph ◽  
Message Passing ◽  
Representation Learning ◽  
Temporal Information ◽  
Graph Representation ◽  
Sequence Information ◽  
Novel Approach ◽  
Graph Neural Networks

We present a novel approach for imputing missing data that incorporates temporal information into bipartite graphs through an extension of graph representation learning. Missing data is abundant in several domains, particularly when observations are made over time. Most imputation methods make strong assumptions about the distribution of the data. While novel methods may relax some assumptions, they may not consider temporality. Moreover, when such methods are extended to handle time, they may not generalize without retraining. We propose using a joint bipartite graph approach to incorporate temporal sequence information. Specifically, the observation nodes and edges with temporal information are used in message passing to learn node and edge embeddings and to inform the imputation task. Our proposed method, temporal setting imputation using graph neural networks (TSI-GNN), captures sequence information that can then be used within an aggregation function of a graph neural network. To the best of our knowledge, this is the first effort to use a joint bipartite graph approach that captures sequence information to handle missing data. We use several benchmark datasets to test the performance of our method against a variety of conditions, comparing to both classic and contemporary methods. We further provide insight to manage the size of the generated TSI-GNN model. Through our analysis we show that incorporating temporal information into a bipartite graph improves the representation at the 30% and 60% missing rate, specifically when using a nonlinear model for downstream prediction tasks in regularly sampled datasets and is competitive with existing temporal methods under different scenarios.

Graph Neural Networks for Prediction of Fuel Ignition Quality

2020 ◽  
Author(s):  
Artur Schweidtmann ◽  
Jan Rittig ◽  
Andrea König ◽  
Martin Grohe ◽  
Alexander Mitsos ◽  
...  
Keyword(s):  
Neural Networks ◽  
Octane Number ◽  
Molecular Graph ◽  
Chemical Properties ◽  
Graph Representation ◽  
Structure Property ◽  
Oxygenated Hydrocarbons ◽  
Physico Chemical ◽  
Ignition Quality ◽  
Graph Neural Networks

<div>Prediction of combustion-related properties of (oxygenated) hydrocarbons is an important and challenging task for which quantitative structure-property relationship (QSPR) models are frequently employed. Recently, a machine learning method, graph neural networks (GNNs), has shown promising results for the prediction of structure-property relationships. GNNs utilize a graph representation of molecules, where atoms correspond to nodes and bonds to edges containing information about the molecular structure. More specifically, GNNs learn physico-chemical properties as a function of the molecular graph in a supervised learning setup using a backpropagation algorithm. This end-to-end learning approach eliminates the need for selection of molecular descriptors or structural groups, as it learns optimal fingerprints through graph convolutions and maps the fingerprints to the physico-chemical properties by deep learning. We develop GNN models for predicting three fuel ignition quality indicators, i.e., the derived cetane number (DCN), the research octane number (RON), and the motor octane number (MON), of oxygenated and non-oxygenated hydrocarbons. In light of limited experimental data in the order of hundreds, we propose a combination of multi-task learning, transfer learning, and ensemble learning. The results show competitive performance of the proposed GNN approach compared to state-of-the-art QSPR models making it a promising field for future research. The prediction tool is available via a web front-end at www.avt.rwth-aachen.de/gnn.</div>

scholarly journals A Survey of Information Cascade Analysis

2021 ◽  
Vol 54 (2) ◽  
pp. 1-36
Author(s):  
Fan Zhou ◽  
Xovee Xu ◽  
Goce Trajcevski ◽  
Kunpeng Zhang
Keyword(s):  
Information Diffusion ◽  
Research Work ◽  
Viral Marketing ◽  
Graph Representation ◽  
Digital Information ◽  
Information Cascades ◽  
Challenges And Opportunities ◽  
Scientific Papers ◽  
Popularity Prediction ◽  
Types Of Information

The deluge of digital information in our daily life—from user-generated content, such as microblogs and scientific papers, to online business, such as viral marketing and advertising—offers unprecedented opportunities to explore and exploit the trajectories and structures of the evolution of information cascades. Abundant research efforts, both academic and industrial, have aimed to reach a better understanding of the mechanisms driving the spread of information and quantifying the outcome of information diffusion. This article presents a comprehensive review and categorization of information popularity prediction methods, from feature engineering and stochastic processes , through graph representation , to deep learning-based approaches . Specifically, we first formally define different types of information cascades and summarize the perspectives of existing studies. We then present a taxonomy that categorizes existing works into the aforementioned three main groups as well as the main subclasses in each group, and we systematically review cutting-edge research work. Finally, we summarize the pros and cons of existing research efforts and outline the open challenges and opportunities in this field.

scholarly journals Temporal Interlacing Network

2020 ◽  
Vol 34 (07) ◽  
pp. 11966-11973
Author(s):  
Hao Shao ◽  
Shengju Qian ◽  
Yu Liu
Keyword(s):  
State Of The Art ◽  
Temporal Information ◽  
Spatial Representations ◽  
The Past ◽  
Temporal Representation ◽  
Temporal Features ◽  
Temporal Models ◽  
Long Time ◽  
Temporal Model ◽  
Spatio Temporal

For a long time, the vision community tries to learn the spatio-temporal representation by combining convolutional neural network together with various temporal models, such as the families of Markov chain, optical flow, RNN and temporal convolution. However, these pipelines consume enormous computing resources due to the alternately learning process for spatial and temporal information. One natural question is whether we can embed the temporal information into the spatial one so the information in the two domains can be jointly learned once-only. In this work, we answer this question by presenting a simple yet powerful operator – temporal interlacing network (TIN). Instead of learning the temporal features, TIN fuses the two kinds of information by interlacing spatial representations from the past to the future, and vice versa. A differentiable interlacing target can be learned to control the interlacing process. In this way, a heavy temporal model is replaced by a simple interlacing operator. We theoretically prove that with a learnable interlacing target, TIN performs equivalently to the regularized temporal convolution network (r-TCN), but gains 4% more accuracy with 6x less latency on 6 challenging benchmarks. These results push the state-of-the-art performances of video understanding by a considerable margin. Not surprising, the ensemble model of the proposed TIN won the 1st place in the ICCV19 - Multi Moments in Time challenge. Code is made available to facilitate further research.1

scholarly journals Pairwise Half-graph Discrimination: A Simple Graph-level Self-supervised Strategy for Pre-training Graph Neural Networks

2021 ◽  
Author(s):  
Pengyong Li ◽  
Jun Wang ◽  
Ziliang Li ◽  
Yixuan Qiao ◽  
Xianggen Liu ◽  
...  
Keyword(s):  
Neural Networks ◽  
Supervised Learning ◽  
Learning Strategy ◽  
Binary Classification ◽  
Representation Learning ◽  
Graph Representation ◽  
Superior Performance ◽  
Graph Classification ◽  
Training Strategy ◽  
Graph Neural Networks

Self-supervised learning has gradually emerged as a powerful technique for graph representation learning. However, transferable, generalizable, and robust representation learning on graph data still remains a challenge for pre-training graph neural networks. In this paper, we propose a simple and effective self-supervised pre-training strategy, named Pairwise Half-graph Discrimination (PHD), that explicitly pre-trains a graph neural network at graph-level. PHD is designed as a simple binary classification task to discriminate whether two half-graphs come from the same source. Experiments demonstrate that the PHD is an effective pre-training strategy that offers comparable or superior performance on 13 graph classification tasks compared with state-of-the-art strategies, and achieves notable improvements when combined with node-level strategies. Moreover, the visualization of learned representation revealed that PHD strategy indeed empowers the model to learn graph-level knowledge like the molecular scaffold. These results have established PHD as a powerful and effective self-supervised learning strategy in graph-level representation learning.

scholarly journals Modeling latent flows on single-cell data using the Hodge decomposition

2019 ◽  
Author(s):  
Kazumitsu Maehara ◽  
Yasuyuki Ohkawa
Keyword(s):  
Diffusion Process ◽  
Single Cell ◽  
Trajectory Analysis ◽  
Single Cells ◽  
Hodge Decomposition ◽  
Biological Data ◽  
Graph Representation ◽  
Specific Cell ◽  
Sparse Graph ◽  
Cell Data

AbstractSingle-cell analysis is a powerful technique used to identify a specific cell population of interest during differentiation, aging, or oncogenesis. Individual cells occupy a particular transient state in the cell cycle, circadian rhythm, or during cell death. An appealing concept of pseudo-time trajectory analysis of single-cell RNA sequencing data was proposed in the software Monocle, and several methods of trajectory analysis have since been published to date. These aim to infer the ordering of cells and enable the tracing of gene expression profile trajectories in cell differentiation and reprogramming. However, the methods are restricted in terms of time structure because of the pre-specified structure of trajectories (linear, branched, tree or cyclic) which contrasts with the mixed state of single cells.Here, we propose a technique to extract underlying flows in single-cell data based on the Hodge decomposition (HD). HD is a theorem of vector fields on a manifold which guarantees that any given flow can decompose into three types of orthogonal component: gradient-flow (acyclic), curl-, and harmonic-flow (cyclic). HD is generalized on a simplicial complex (graph) and the discretized HD has only a weak assumption that the graph is directed. Therefore, in principle, HD can extract flows from any mixture of tree and cyclic time flows of observed cells. The decomposed flows provide intuitive interpretations about complex flow because of their linearity and orthogonality. Thus, each extracted flow can be focused on separately with no need to consider crosstalk.We developed ddhodge software, which aims to model the underlying flow structure that implies unobserved time or causal relations in the hodge-podge collection of data points. We demonstrated that the mathematical framework of HD is suitable to reconstruct a sparse graph representation of diffusion process as a candidate model of differentiation while preserving the divergence of the original fully-connected graph. The preserved divergence can be used as an indicator of the source and sink cells in the observed population. A sparse graph representation of the diffusion process transforms data analysis of the non-linear structure embedded in the high-dimensional space of single-cell data into inspection of the visible flow using graph algorithms. Hence, ddhodge is a suitable toolkit to visualize, inspect, and subsequently interpret large data sets including, but not limited to, high-throughput measurements of biological data.The beta version of ddhodge R package is available at:https://github.com/kazumits/ddhodge

scholarly journals UniGNN: a Unified Framework for Graph and Hypergraph Neural Networks

2021 ◽  
Author(s):  
Jing Huang ◽  
Jie Yang
Keyword(s):  
Neural Networks ◽  
Message Passing ◽  
State Of The Art ◽  
Representation Learning ◽  
Graph Representation ◽  
Challenging Problem ◽  
Unified Framework ◽  
Real World Datasets ◽  
Graph Neural Networks ◽  
Research Domains

Hypergraph, an expressive structure with flexibility to model the higher-order correlations among entities, has recently attracted increasing attention from various research domains. Despite the success of Graph Neural Networks (GNNs) for graph representation learning, how to adapt the powerful GNN-variants directly into hypergraphs remains a challenging problem. In this paper, we propose UniGNN, a unified framework for interpreting the message passing process in graph and hypergraph neural networks, which can generalize general GNN models into hypergraphs. In this framework, meticulously-designed architectures aiming to deepen GNNs can also be incorporated into hypergraphs with the least effort. Extensive experiments have been conducted to demonstrate the effectiveness of UniGNN on multiple real-world datasets, which outperform the state-of-the-art approaches with a large margin. Especially for the DBLP dataset, we increase the accuracy from 77.4% to 88.8% in the semi-supervised hypernode classification task. We further prove that the proposed message-passing based UniGNN models are at most as powerful as the 1-dimensional Generalized Weisfeiler-Leman (1-GWL) algorithm in terms of distinguishing non-isomorphic hypergraphs. Our code is available at https://github.com/OneForward/UniGNN.

scholarly journals Learning Diffusions without Timestamps

2019 ◽  
Vol 33 ◽  
pp. 582-589
Author(s):  
Hao Huang ◽  
Qian Yan ◽  
Ting Gan ◽  
Di Niu ◽  
Wei Lu ◽  
...  
Keyword(s):  
Diffusion Process ◽  
Real World ◽  
Probabilistic Model ◽  
Network Inference ◽  
Diffusion Processes ◽  
Temporal Information ◽  
Exact Time ◽  
Effectiveness And Efficiency ◽  
Parent Child

To learn the underlying parent-child influence relationships between nodes in a diffusion network, most existing approaches require timestamps that pinpoint the exact time when node infections occur in historical diffusion processes. In many real-world diffusion processes like the spread of epidemics, monitoring such infection temporal information is often expensive and difficult. In this work, we study how to carry out diffusion network inference without infection timestamps, using only the final infection statuses of nodes in each historical diffusion process, which are more readily accessible in practice. Our main result is a probabilistic model that can find for each node an appropriate number of most probable parent nodes, who are most likely to have generated the historical infection results of the node. Extensive experiments on both synthetic and real-world networks are conducted, and the results verify the effectiveness and efficiency of our approach.

scholarly journals GSSNN: Graph Smoothing Splines Neural Networks

2020 ◽  
Vol 34 (04) ◽  
pp. 7007-7014
Author(s):  
Shichao Zhu ◽  
Lewei Zhou ◽  
Shirui Pan ◽  
Chuan Zhou ◽  
Guiying Yan ◽  
...  
Keyword(s):  
Neural Networks ◽  
State Of The Art ◽  
Representation Learning ◽  
Smoothing Splines ◽  
Graph Representation ◽  
Graph Classification ◽  
Topological Information ◽  
Graph Representations ◽  
The Arts ◽  
Graph Neural Networks

Graph Neural Networks (GNNs) have achieved state-of-the-art performance in many graph data analysis tasks. However, they still suffer from two limitations for graph representation learning. First, they exploit non-smoothing node features which may result in suboptimal embedding and degenerated performance for graph classification. Second, they only exploit neighbor information but ignore global topological knowledge. Aiming to overcome these limitations simultaneously, in this paper, we propose a novel, flexible, and end-to-end framework, Graph Smoothing Splines Neural Networks (GSSNN), for graph classification. By exploiting the smoothing splines, which are widely used to learn smoothing fitting function in regression, we develop an effective feature smoothing and enhancement module Scaled Smoothing Splines (S3) to learn graph embedding. To integrate global topological information, we design a novel scoring module, which exploits closeness, degree, as well as self-attention values, to select important node features as knots for smoothing splines. These knots can be potentially used for interpreting classification results. In extensive experiments on biological and social datasets, we demonstrate that our model achieves state-of-the-arts and GSSNN is superior in learning more robust graph representations. Furthermore, we show that S3 module is easily plugged into existing GNNs to improve their performance.

Sign in / Sign up

Export Citation Format

Share Document