Predicting hate intensity of twitter conversation threads

Tweets are the most concise form of communication in online social media. Wherein a single tweet has the potential to make or break the discourse of the conversation. Online hate speech is more accessible than ever, and stifling its propagation is of utmost importance for social media companies and users for congenial communication. Most of the research has focused on classifying an individual tweet regardless of the tweet thread/context leading up to that point. One of the classical approaches to curb hate speech is to adopt a reactive strategy after the hateful content has been published. This strategy results in neglecting subtle posts that do not show the potential to instigate hate speech on their own but may portend in the subsequent discussion ensuing in the post's replies. In this paper, we propose DRAGNET++, which aims to predict the intensity of hatred that a tweet can bring in through its reply chain in the future. Our model uses the semantic and propagating structure of the tweet threads to maximize the contextual information leading up to and the fall of hate intensity at each subsequent tweet. We explore three publicly available Twitter datasets – Anti-Racism contains the reply tweets of a collection of social media discourse on racist remarks during US political and COVID-19 background;Anti-Social presents a dataset of 40 million tweets amidst the COVID-19 pandemic on anti-social behaviours with custom annotations;and Anti-Asian presents Twitter datasets collated based on anti-Asian behaviours during COVID-19 pandemic. All the curated datasets consist of structural graph information of the Tweet threads. We show that DRAGNET++ outperforms all the state-of-the-art baselines significantly. It beats the best baseline by an 11% margin on the Person correlation coefficient and a decrease of 25% on RMSE for the Anti-Racism dataset with a similar performance on the other two datasets.

A precise and timely graph‐based approach to identify SARS Covid19 infection from medical imaging data using IsoCovNet

More than 100 million individuals have been infected by the COVID19 virus since 2019. Even if the vaccination procedure has already begun, it will take time to attain an adequate supply. There have been several efforts by computer scientists to filter COVID19 from CXR or CT scans due to the disease's extensive prevalence. These patients' CT and CXR scans are utilized to identify COVID19 using IsoCovNet, a Graph‐Isomorphic‐Network, that is, GIN‐based model for detecting COVID19. A GIN‐based design dictates that our suggested model only takes data in the form of graphs. At the outset, the input image undergoes a conversion into an unordered network, that is, a graph that considers only the links between elements rather than the entire image. This approach significantly reduces the model's processing time. We verified the effectiveness of our proposed IsoCovNet network by using four datasets, which consist of both x‐ray and CT‐scan images, from five standard sources that are publicly available on platforms like Kaggle and GitHub. The network achieved an accuracy of 99.51% on binary datasets and a higher accuracy of 99.84% on the multi‐classification task of detecting Covid19. [ FROM AUTHOR] Copyright of International Journal of Imaging Systems & Technology is the property of John Wiley & Sons, Inc. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full . (Copyright applies to all s.)

Fusing hybrid attentive network with self-supervised dual-channel heterogeneous graph for knowledge tracing

Recently the large-scale influence of Covid-19 promoted the fast development of intelligent tutoring systems (ITS). As a major task of ITS, Knowledge Tracing (KT) aims to capture a student's dynamic knowledge state based on his historical response sequences and provide personalized learning assistance to him. However, most existing KT methods have encountered the data sparsity problem. In real scenarios, an online tutoring system usually has an extensive collection of questions while each student can only interact with a limited number of questions. As a result, the records of some questions could be extremely sparse, which degrades the performance of traditional KT models. To resolve this issue, we propose a Dual-channel Heterogeneous Graph Network (DHGN) to learn informative representations of questions from students' records by capturing both the high-order heterogeneous and local relations. As the supervised learning manner applied in previous methods is incapable of exploiting unobserved relations between questions, we innovatively integrate a self-supervised framework into the KT task and employ contrastive learning via the two channels of DHGN, supplementing as an auxiliary task to improve the KT performance. Moreover, we adopt the attention mechanism, which has achieved impressive performance in natural language processing tasks, to effectively capture students' knowledge state. But the standard attention network is inapplicable to the KT task because the current knowledge state of a student usually shows strong dependency on his recently interactive questions, unlike the situation of language processing tasks, which focus more on the long-term dependency. To avoid the inefficiency of standard attention networks in the KT task, we further devise a novel Hybrid Attentive Network (HAN), which produces both the global attention and the hierarchical local attention to model the long-term and short-term intents, respectively. Then, by the gating network, a student's long-term and short-term intents are combined for efficient prediction. We conduct extensive experiments on several real-world datasets. Experimental results demonstrate that our proposed methods achieve significant performance improvement compared to existing state-of-the-art baselines, which validates the effectiveness of the proposed dual-channel heterogeneous graph framework and hybrid attentive network. © 2023 Elsevier Ltd

Contact Tracing and Epidemic Intervention via Deep Reinforcement Learning

The recent outbreak of COVID-19 poses a serious threat to people's lives. Epidemic control strategies have also caused damage to the economy by cutting off humans' daily commute. In this article, we develop an Individual-based Reinforcement Learning Epidemic Control Agent (IDRLECA) to search for smart epidemic control strategies that can simultaneously minimize infections and the cost of mobility intervention. IDRLECA first hires an infection probability model to calculate the current infection probability of each individual. Then, the infection probabilities together with individuals' health status and movement information are fed to a novel GNN to estimate the spread of the virus through human contacts. The estimated risks are used to further support an RL agent to select individual-level epidemic-control actions. The training of IDRLECA is guided by a specially designed reward function considering both the cost of mobility intervention and the effectiveness of epidemic control. Moreover, we design a constraint for control-action selection that eases its difficulty and further improve exploring efficiency. Extensive experimental results demonstrate that IDRLECA can suppress infections at a very low level and retain more than 95% of human mobility. © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM.

LigBind: Identifying Binding Residues for Over 1000 Ligands with Relation-Aware Graph Neural Networks.

Identifying the interactions between proteins and ligands is significant for drug discovery and design. Considering the diverse binding patterns of ligands, the ligand-specific methods are trained per ligand to predict binding residues. However, most of the existing ligand-specific methods ignore shared binding preferences among various ligands and generally only cover a limited number of ligands with a sufficient number of known binding proteins. In this study, we propose a relation-aware framework LigBind with graph-level pre-training to enhance the ligand-specific binding residue predictions for 1159 ligands, which can effectively cover the ligands with a few known binding proteins. LigBind first pre-trains a graph neural network-based feature extractor for ligand-residue pairs and relation-aware classifiers for similar ligands. Then, LigBind is fine-tuned with ligand-specific binding data, where a domain adaptive neural network is designed to automatically leverage the diversity and similarity of various ligand-binding patterns for accurate binding residue prediction. We construct ligand-specific benchmark datasets of 1159 ligands and 16 unseen ligands, which are used to evaluate the effectiveness of LigBind. The results demonstrate the LigBind's efficacy on large-scale ligand-specific benchmark datasets, and it generalizes well to unseen ligands. LigBind also enables accurate identification of the ligand-binding residues in the main protease, papain-like protease and the RNA-dependent RNA polymerase of SARS-CoV-2. The web server and source codes of LigBind are available at http://www.csbio.sjtu.edu.cn/bioinf/LigBind/ and https://github.com/YYingXia/LigBind/ for academic use.

Hourly forecasting of traffic flow rates using spatial temporal graph neural networks.

Traffic congestion forms a large problem in many major metropolitan regions around the world, leading to delays and societal costs. As people resume travel upon relaxation of COVID-19 restrictions and personal mobility returns to levels prior to the pandemic, policy makers need tools to understand new patterns in the daily transportation system. In this paper we use a Spatial Temporal Graph Neural Network (STGNN) to train data collected by 34 traffic sensors around Amsterdam, in order to forecast traffic flow rates on an hourly aggregation level for a quarter. Our results show that STGNN did not outperform a baseline seasonal naive model overall, however for sensors that are located closer to each other in the road network, the STGNN model did indeed perform better.

EpiGNN: Exploring Spatial Transmission with Graph Neural Network for Regional Epidemic Forecasting

Epidemic forecasting is the key to effective control of epidemic transmission and helps the world mitigate the crisis that threatens public health. To better understand the transmission and evolution of epidemics, we propose EpiGNN, a graph neural network-based model for epidemic forecasting. Specifically, we design a transmission risk encoding module to characterize local and global spatial effects of regions in epidemic processes and incorporate them into the model. Meanwhile, we develop a Region-Aware Graph Learner (RAGL) that takes transmission risk, geographical dependencies, and temporal information into account to better explore spatial-temporal dependencies and makes regions aware of related regions' epidemic situations. The RAGL can also combine with external resources, such as human mobility, to further improve prediction performance. Comprehensive experiments on five real-world epidemic-related datasets (including influenza and COVID-19) demonstrate the effectiveness of our proposed method and show that EpiGNN outperforms state-of-the-art baselines by 9.48% in RMSE. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Explainable Prediction of the Severity of COVID-19 Outbreak for US Counties

Ever since the COVID-19 outbreak, various works have focused on using multitude of different static and dynamic features to aid the prediction of disease forecasting models. However, in the absence of historical pandemic data these models will not be able to give any meaningful insight about the areas which are most likely to be affected based on preexisting conditions. Furthermore, the black box nature of neural networks often becomes an impediment for the concerned authorities to derive any meaning from. In this paper, we propose a novel explainable Graph Neural Network (GNN) framework called Graph-COVID-19-Explainer (GC-Explainer) that gives explainable prediction for the severity of the spread during initial outbreak. We utilize a comprehensive set of static population characteristics to use as node features of Graph where each node corresponds to a geographical region. Unlike post-hoc methods of GNN explanations, we propose a framework for learning important features during the training of the model. We further apply our model on real-world early pandemic data to show the validity of our approach. Through GC-Explainer, we show that static features along with spatial dependency among regions can be used to explain the varied degree of severity in outbreak during the early part of the pandemic and provide a framework to identify the at-risk areas for any infectious disease outbreak, especially when historical data is not available. © 2022 IEEE.

Graph Convolutional Capsule Regression (GCCR): A Model for Accelerated Filtering of Novel Potential Candidates for SARS-CoV-2 Based on Binding Affinity.

BACKGROUND: There has been a growing interest in discovering a viable drug for the new coronavirus (SARS-CoV-2) since the beginning of the pandemic. Protein-ligand interaction studies are a crucial step in the drug discovery process, as it helps us narrow the search space for potential ligands with high drug-likeness. Derivatives of popular drugs like Remdesivir generated through tools employing evolutionary algorithms are usually considered potential candidates. However, screening promising molecules from such a large search space is difficult. In a conventional screening process, for each ligand-target pair, there are time-consuming interaction studies that use docking simulations before downstream tasks like thermodynamic, kinetic, and electrostatic-potential evaluation. METHODS: In this work, 'Graph Convolutional Capsule Regression' (GCCR), a model which uses Capsule Neural Networks (CapsNet) and Graph Convolutional Networks (GCN) to predict the binding energy of a protein-ligand complex is being proposed. The model's predictions were further validated with kinetic and free energy studies like Molecular Dynamics (MD) for kinetic stability and MM/GBSA analysis for free energy calculations. RESULTS: The GCCR showed an RMSE value of 0.0978 for 81.3% of the concordance index. The RMSE of GCCR converged around the iteration of just 50 epochs scoring a lower RMSE than GCN and GAT. When training with Davis Dataset, GCCR gave an RMSE score of 0.3806 with a CI score of 87.5%. CONCLUSION: The proposed GCCR model shows great potential in improving the screening process based on binding affinity and outperforms baseline machine learning models like DeepDTA, KronRLS, SimBoost, and other Graph Neural Networks (GNN) based models like Graph Convolutional Networks (GCN) and Graph Attention Networks (GAT).

Fake news detection: A survey of graph neural network methods.

The emergence of various social networks has generated vast volumes of data. Efficient methods for capturing, distinguishing, and filtering real and fake news are becoming increasingly important, especially after the outbreak of the COVID-19 pandemic. This study conducts a multiaspect and systematic review of the current state and challenges of graph neural networks (GNNs) for fake news detection systems and outlines a comprehensive approach to implementing fake news detection systems using GNNs. Furthermore, advanced GNN-based techniques for implementing pragmatic fake news detection systems are discussed from multiple perspectives. First, we introduce the background and overview related to fake news, fake news detection, and GNNs. Second, we provide a GNN taxonomy-based fake news detection taxonomy and review and highlight models in categories. Subsequently, we compare critical ideas, advantages, and disadvantages of the methods in categories. Next, we discuss the possible challenges of fake news detection and GNNs. Finally, we present several open issues in this area and discuss potential directions for future research. We believe that this review can be utilized by systems practitioners and newcomers in surmounting current impediments and navigating future situations by deploying a fake news detection system using GNNs.

Human migration-based graph convolutional network for PM2.5 forecasting in post-COVID-19 pandemic age.

Due to the coronavirus disease 2019 pandemic, local authorities always implanted non-pharmaceutical interventions, such as maintaining social distance to reduce human migration. Besides, previous studies have proved that human migration highly influenced air pollution concentration in an area. Therefore, this study aims to explore whether human migration can work as a significant factor in the post-pandemic age to help PM2.5 concentration forecasting. In this work, we first analyze the variations of PM2.5 in 11 cities of Hubei from 2015 to 2020 and further compare PM2.5 trends with the migration trends of Hubei province in 2020. Experimental results indicate that the human migration indirectly affected the urban PM2.5 concentration. Then, we established a graph data structure based on the migration network describing the migration flow size between any two areas in the Hubei province and proposed a migration attentive graph convolutional network (MAGCN) for forecasting PM2.5. Combined with the migration data. The proposed model can attentively aggregate the information of neighbor nodes through migration weights. Experimental results indicate that the proposed MAGCN can forecast PM2.5 concentration accurately.

ESA-FedGNN: Efficient secure aggregation for federated graph neural networks.

Graph Neural Network (GNN) architecture is a state-of-the-art model, which can obtain complete node embedding features and rich data information by aggregating the information of nodes and neighbors. Therefore, GNNs are widely used in electronic shopping, drug discovery (especially for the treatment of COVID-19) and other fields, promoting the explosive development of machine learning. However, user interaction, data sharing and circulation are highly sensitive to privacy, and centralized storage can lead to data isolation. Therefore, Federated Learning with high efficiency and strong security and privacy enhancement technology based on secure aggregation can improve the security dilemma faced by GNN. In this paper, we propose an Efficient Secure Aggregation for Federated Graph Neural Network(ESA-FedGNN), which can efficiently reduce the cost of communication and avoid computational redundancy while ensuring data privacy. Firstly, a novel secret sharing scheme based on numerical analysis is proposed, which employs Fast Fourier Transform to improve the computational power of the neural network in sharing phase, and leverages Newton Interpolation method to deal with the disconnection and loss of the client in reconstruction phase. Secondly, a regular graph embedding based on geometric distribution is proposed, which optimizes the aggregation speed by using data parallelism. Finally, a double mask is adopted to ensure privacy and prevent malicious adversaries from stealing model parameters. We achieve O ( log N log ( log N ) ) improvements compared to O N 2 in state-of-the-art works. This research helps to provide security solutions related to the practical development and application of privacy-preserving graph neural network technology.

Determining similarities of COVID-19 - lung cancer drugs and affinity binding mode analysis by graph neural network-based GEFA method.

COVID-19 is a worldwide health crisis seriously endangering the arsenal of antiviral and antibiotic drugs. It is urgent to find an effective antiviral drug against pandemic caused by the severe acute respiratory syndrome (Sars-Cov-2), which increases global health concerns. As it can be expensive and time-consuming to develop specific antiviral drugs, reuse of FDA-approved drugs that provide an opportunity to rapidly distribute effective therapeutics can allow to provide treatments with known preclinical, pharmacokinetic, pharmacodynamic and toxicity profiles that can quickly enter in clinical trials. In this study, using the structural information of molecules and proteins, a list of repurposed drug candidates was prepared again with the graph neural network-based GEFA model. The data set from the public databases DrugBank and PubChem were used for analysis. Using the Tanimoto/jaccard similarity analysis, a list of similar drugs was prepared by comparing the drugs used in the treatment of COVID-19 with the drugs used in the treatment of other diseases. The resultant drugs were compared with the drugs used in lung cancer and repurposed drugs were obtained again by calculating the binding strength between a drug and a target. The kinase inhibitors (erlotinib, lapatinib, vandetanib, pazopanib, cediranib, dasatinib, linifanib and tozasertib) obtained from the study can be used as an alternative for the treatment of COVID-19, as a combination of blocking agents (gefitinib, osimertinib, fedratinib, baricitinib, imatinib, sunitinib and ponatinib) such as ABL2, ABL1, EGFR, AAK1, FLT3 and JAK1, or antiviral therapies (ribavirin, ritonavir-lopinavir and remdesivir).Communicated by Ramaswamy H. Sarma.

Molecule generation toward target protein (SARS-CoV-2) using reinforcement learning-based graph neural network via knowledge graph.

AI-driven approaches are widely used in drug discovery, where candidate molecules are generated and tested on a target protein for binding affinity prediction. However, generating new compounds with desirable molecular properties such as Quantitative Estimate of Drug-likeness (QED) and Dopamine Receptor D2 activity (DRD2) while adhering to distinct chemical laws is challenging. To address these challenges, we proposed a graph-based deep learning framework to generate potential therapeutic drugs targeting the SARS-CoV-2 protein. Our proposed framework consists of two modules: a novel reinforcement learning (RL)-based graph generative module with knowledge graph (KG) and a graph early fusion approach (GEFA) for binding affinity prediction. The first module uses a gated graph neural network (GGNN) model under the RL environment for generating novel molecular compounds with desired properties and a custom-made KG for molecule screening. The second module uses GEFA to predict binding affinity scores between the generated compounds and target proteins. Experiments show how fine-tuning the GGNN model under the RL environment enhances the molecules with desired properties to generate 100 % valid and 100 % unique compounds using different scoring functions. Additionally, KG-based screening reduces the search space of generated candidate molecules by 96.64 % while retaining 95.38 % of promising binding molecules against SARS-CoV-2 protein, i.e., 3C-like protease (3CLpro). We achieved a binding affinity score of 8.185 from the top rank of generated compound. In addition, we compared top-ranked generated compounds to Indinavir on different parameters, including drug-likeness and medicinal chemistry, for qualitative analysis from a drug development perspective. Supplementary Information: The online version contains supplementary material available at 10.1007/s13721-023-00409-2.

Graph and Capsule Convolutional Neural Network Based Classification of Lung Cancer, Pneumonia, COVID-19 using Lung CT and Ultrasound Radiography Imaging

Pulmonary / Lung nodules are a sign of lung cancer. Pneumonia, Lung nodules show up on imaging scans like X-rays, CT or ultrasound scans. The healthcare team may refer to the growth as a spot on the lung, coin lesion, or shadow. Coronavirus (COVID-19) has been identified as a worldwide epidemic, affecting individuals all over the nation. It is vital to identify COVID-19-affected persons to limit the virus's spread. According to the latest study, radiographic approaches can be used to diagnose contamination utilizing deep learning (DL) methods. Considering that DL is a valuable approach and methodology for image analysis, various studies on COVID-19 case detection utilizing radiographs to train DL networks have been conducted. Although just a handful of studies presume to have excellent prediction results, their proposed systems may suffer from a restricted amount of data. Employing graph and capsule, Convolutional Neural Network (CNN) can overcome the shortcomings by predicting multiple disorders using a single network implemented in a hospital. We present a novel comparative method that has paved the way for an open-source COVID-19 case classification approach based on graph and capsule images with CT and ultrasound. Experimental results show that the Capsule network attained the best 98.93% AUC, 99.2% accuracy, 98.4% Fl-score, 98.40% sensitivity, 98.40% specificity, 9S.4l% precision using CT labels. Whereas the ultrasound test set the graph network performed well with 96.93% AUC, 97.26% accuracy, 95.92% Fl-score, 95.90% sensitivity, 97.94% specificity, 96.08% precision. © 2022 IEEE.

Substation Safety Awareness Intelligent Model: Fast Personal Protective Equipment Detection using GNN Approach

Federal regulations require employees to protect themselves from electrical hazards when working at substations. Such protections, commonly called personal protective equipment (PPE), vary with the hazard types and nature of exposure or delivery. Over the past decades, personal injuries and fatalities from electrical hazards have remained relatively common despite regular risk assessments and controls. One reason for this is that adequate PPE is not appropriately used. Easy-to-deploy strategies to detect proper use of PPE for electrical hazards are not available. Here, an intelligent detection model is developed to check whether PPE is appropriately worn or not;warning alarms would be triggered when the usage does not follow safety regulations. Arc-flash analysis is employed to determine a reasonable and safe PPE guideline. Eight types of PPE are considered, which cover the major PPE categories utilized in practice, including medical masks recommended for the Covid-19 pandemic. The model's framework utilizes a few-shot based graph neural network (GNN) technique to detect PPE. In contrast to prior data-driven models, only 50 images were collected for each PPE type, a relatively small number compared with state-of-the-art research. The proposed model was trained with diversified samples within multiple environments, resulting in a robust, efficient, intelligent detection model with probability of similarity in the range of 79%- 100%. To tackle the existing issues of computer-vision based PPE detection models, some technical suggestions on preserving personal privacy and PPE labels are provided. IEEE

Research on COVID-19 document fine-grained classification based on graph neural network

Since the outbreak of COVID-19, academia has published tens of thousands of new papers. Facing so much literature knowledge, how to realize the fine-grained classification of covid-19 literature and help researchers carry out research? This is an urgent problem to be solved. This paper makes COVID-19 text classification graph data set, designs covid-19 scientific literature fine-grained classification model LC-GAT based on graph attention network, adds attention mechanism at word level, sentence level and graph level, effectively retains the classification information contained in article title and key words, and significantly improves the performance of covid-19 scientific literature fine-grained classification. This paper has positive significance for the classification of COVID-19 scientific literature. © 2022 IEEE.

Reviving the economy while saving lives: a deep reinforcement learning approach for smart POI reopening

With the gradual improvements in COVID-19 metrics and the accelerated immunization progress, countries around the world have began to focus on reviving the economy while continuously strengthening epidemic control. POInt-of-Interest (POI) reopening, as a necessity for restoring human mobilities, has become a crucial step to recouple economic recovery and public health management. In contrast to the lock-down policy, POI reopening demands a dynamic trade-off between epidemic interventions and economic costs. In the urban scenario, there exist three key challenges in developing effective POI reopening strategies as follows. (1) During the POI reopening process, there are multiple urban factors affecting the epidemic transmission, which are difficult to simultaneously incorporate and balance in a single reopening strategy;(2) the effects of POI reopening on both economic recovery and epidemic control are long-term, which are hard to capture by static models;and (3) the dual objectives of minimizing infections and maintaining POIs' visits are conflicting, making it difficult to achieve a flexible and scalable trade-off. To tackle the above challenges, we propose Reopener, a deep reinforcement learning (RL) framework for smart POI reopening. First, we utilize a bipartite graph neural network to automatically encode all urban factors that would affect the epidemic prevention and POI visit restriction. Second, we employ a RL-based deep policy network to enable flexible updates in restrictions on POIs along with the trend of epidemic. Third, we design a novel reward function to guide the RL agent to learn smartly, thus comprehensively trading off infections and visit sustainability of POIs. Extensive experimental results demonstrate that Reopener outperforms all baseline methods with remarkable improvements, by reducing the overall economic cost by at least 6.42%. Reopener can effectively suppress infections and support a phase-based POI reopening process, which provides valuable insights for strategy design in post-COVID-19 economic recovery. © 2022 Owner/Author.

Spatio-temporal Graph Convolution BiLSTM for COVID-19 Community Mobility

Google COVID-19 community mobility data is important information to reflect the level of social activity and infer economic development. However, the data has complexity and non-linear spatiotemporal characteristics, and it is difficult for traditional prediction algorithms to fit such data with both temporal and spatial characteristics. To address such problems, this paper proposes a novel Spatio-temporal Graph Convolution Bidirectional Long Short Term Memory (STGC-BiLSTM) deep learning model, in which, the spatio-temporal graph convolution module can simultaneously mine the temporal and spatial features, and the prediction module encodes and regresses these features to complete the prediction of Google's mobile indices. The experiments show that the STGC-BiLSTM exhibits superior performance for both single-step and multi-step prediction for the four national datasets. Finally, ablation experiments are used to verify the effects of the spatio-temporal graph convolution module and regularization parameters to further illustrate the effectiveness of the model proposed in this paper. © 2022 IEEE.

Self-supervised heterogeneous hypergraph network for knowledge tracing

Recently online intelligent education has caught more and more attention, especially due to the global influence of Covid-19. A major task of intelligent education is Knowledge Tracing (KT) which aims to capture students' dynamic status based on their historical interaction records and predict their responses to new questions. However, most existing KT methods suffer from the record data sparsity problem. In reality, there are a huge number of questions in the online database and students can only interact with a very small set of these questions. The records of some questions could be extremely sparse, which may significantly degrade the performance of traditional KT methods. Although recent graph neural network (GNN) based KT methods can fuse graph-structured information and improve the representation of questions to some extent, the pairwise structure of GNN neglects the complex high-order and heterogeneous relations among questions. To resolve the above issues, we develop a novel KT model with the heterogeneous hypergraph network (HHN) and propose an attentive mechanism, including intra- and inter-graph attentions, to aggregate neighbors' information upon HHN. To further enhance the question representation, we supplement the supervised prediction task of KT with an auxiliary self-supervised task, i.e., we additionally generate an augmented view with adaptive data augmentation to implement contrastive learning and exploit the unobserved relations among questions. We conduct extensive experiments on several real-world datasets. Experimental results demonstrate that our proposed method achieves significant performance improvement compared to some state-of-the-art KT methods.