Skip to main content
Erschienen in: Neural Computing and Applications 7/2024

06.12.2023 | Original Article

Multi-level contrastive graph learning for academic abnormality prediction

verfasst von: Yong Ouyang, Yuanlin Wang, Rong Gao, Yawen Zeng, Jinhang Liu, Zhiwei Ye

Erschienen in: Neural Computing and Applications | Ausgabe 7/2024

Einloggen

Aktivieren Sie unsere intelligente Suche um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

Academic Abnormality Prediction aims to predict whether students have academic abnormalities through their historical academic scores. However, existing research methods still have the following challenges: (1) Student behavior. Only the students’ historical academic performance is considered, ignoring the impact of student behavior in student status. (2) Data imbalance. The number of academically abnormal students is much less than that of ordinary students, resulting in a data imbalance problem. Therefore, in response to the above challenges, this paper proposes a Multi-level Contrastive Graph learning for academic abnormality prediction (MCG). Specifically, firstly, we capture student behavior and fuse it with student historical achievement data based on a Graph Neural Network (GNN), Thereafter, we construct an embedding space for sample interpolation, which generates virtual nodes of abnormal students, thereby alleviating the data imbalance problem. Moreover, we introduce a multi-level contrastive learning module to precisely learn node representations and maximize the consistency between different views of the same node in the target and online networks for data augmentation. Experiments on real datasets show that the abnormality prediction performance of MCG outperforms the existing state-of-the-art methods.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Literatur
1.
Zurück zum Zitat Wang S (2014) Analysis of educational data mining to promote personalized learning pathways for college students. Exam Weekly, pp 176 Wang S (2014) Analysis of educational data mining to promote personalized learning pathways for college students. Exam Weekly, pp 176
2.
Zurück zum Zitat Livieris IE, Kotsilieris T, Tampakas V et al (2019) Improving the evaluation process of students’ performance utilizing a decision support software. Neural Comput Appl 31(6):1683–1694CrossRef Livieris IE, Kotsilieris T, Tampakas V et al (2019) Improving the evaluation process of students’ performance utilizing a decision support software. Neural Comput Appl 31(6):1683–1694CrossRef
3.
Zurück zum Zitat Nabil A, Seyam M, Abou-Elfetouh Ahmed (2021) Prediction of students’ academic performance based on courses grades using deep neural networks. IEEE Access 9:140731–140746CrossRef Nabil A, Seyam M, Abou-Elfetouh Ahmed (2021) Prediction of students’ academic performance based on courses grades using deep neural networks. IEEE Access 9:140731–140746CrossRef
4.
Zurück zum Zitat Xing W, Guo R, Petakovic E et al (2015) Participation-based student final performance prediction model through interpretable Genetic Programming: Integrating learning analytics, educational data mining and theory. Comput Human Behav 47:168–181CrossRef Xing W, Guo R, Petakovic E et al (2015) Participation-based student final performance prediction model through interpretable Genetic Programming: Integrating learning analytics, educational data mining and theory. Comput Human Behav 47:168–181CrossRef
5.
Zurück zum Zitat Feng G, Fan M, Chen Y (2022) Analysis and prediction of students’ academic performance based on educational data mining. IEEE Access 10:19558–19571CrossRef Feng G, Fan M, Chen Y (2022) Analysis and prediction of students’ academic performance based on educational data mining. IEEE Access 10:19558–19571CrossRef
6.
Zurück zum Zitat Tao B, Liu K, Miao F et al (2019) Design of Early Warning System for Student’s Poor Academic Performance Based on SVM Improved by KFCM. Research And Exploration In Laboratory 38(5) Tao B, Liu K, Miao F et al (2019) Design of Early Warning System for Student’s Poor Academic Performance Based on SVM Improved by KFCM. Research And Exploration In Laboratory 38(5)
7.
Zurück zum Zitat Sun Z, Lu C, Shi Z et al (2016) Research and advances on deep learning. Comput Sci 43(2):1–8 Sun Z, Lu C, Shi Z et al (2016) Research and advances on deep learning. Comput Sci 43(2):1–8
8.
Zurück zum Zitat Shaoping Jiang (2021) Correlation analysis of student behavior and improvement of GA-BP academic early warning algorithm. Comput Syst Appl 30(4):199–203 Shaoping Jiang (2021) Correlation analysis of student behavior and improvement of GA-BP academic early warning algorithm. Comput Syst Appl 30(4):199–203
9.
Zurück zum Zitat Mubarak A, Cao H, Hezam I (2021) Deep analytic model for student dropout prediction in massive open online courses. Comput Electr Eng 93:107271CrossRef Mubarak A, Cao H, Hezam I (2021) Deep analytic model for student dropout prediction in massive open online courses. Comput Electr Eng 93:107271CrossRef
10.
Zurück zum Zitat Zeng Y, Ouyang Y, Gao R et al (2020) Elective future: the influence factor mining of students’ graduation development based on hierarchical attention neural network model with graph. Appl Intell 50(10):3023–3039CrossRef Zeng Y, Ouyang Y, Gao R et al (2020) Elective future: the influence factor mining of students’ graduation development based on hierarchical attention neural network model with graph. Appl Intell 50(10):3023–3039CrossRef
11.
Zurück zum Zitat Hai-tao P, Ming-qu F, Hong-bin Z et al (2021) Predicting academic performance of students in Chinese-foreign cooperation in running schools with graph convolutional network. Neural Comput Appl 33(2):637–645CrossRef Hai-tao P, Ming-qu F, Hong-bin Z et al (2021) Predicting academic performance of students in Chinese-foreign cooperation in running schools with graph convolutional network. Neural Comput Appl 33(2):637–645CrossRef
12.
Zurück zum Zitat Liu M, Shao P, Zhang K (2021) Graph-Based Exercise-and Knowledge-Aware Learning Network for Student Performance Prediction. CAAI International Conference on Artificial Intelligence, pp 27-38 Liu M, Shao P, Zhang K (2021) Graph-Based Exercise-and Knowledge-Aware Learning Network for Student Performance Prediction. CAAI International Conference on Artificial Intelligence, pp 27-38
13.
Zurück zum Zitat Lu X, Zhu Y, Xu Y et al (2021) Learning from multiple dynamic graphs of student and course interactions for student grade predictions. Neurocomputing 431:23–33CrossRef Lu X, Zhu Y, Xu Y et al (2021) Learning from multiple dynamic graphs of student and course interactions for student grade predictions. Neurocomputing 431:23–33CrossRef
14.
Zurück zum Zitat Tan G, Xu F, Qu W (2016) Factors and models influencing students’ behavioral intention to teach online in higher education. e-Education Research, pp 47–53 Tan G, Xu F, Qu W (2016) Factors and models influencing students’ behavioral intention to teach online in higher education. e-Education Research, pp 47–53
15.
Zurück zum Zitat Chi LP, Xin ZQ (2006) Measurement of college students’ learning motivation and its relationship with self-efficacy. Psychol Dev Edu 22(2):64–70 Chi LP, Xin ZQ (2006) Measurement of college students’ learning motivation and its relationship with self-efficacy. Psychol Dev Edu 22(2):64–70
16.
Zurück zum Zitat He XM, Chen XM (2008) A study on the influence of students’ learning engagement on learning interest. Global Edu Outlook 3:46–51 He XM, Chen XM (2008) A study on the influence of students’ learning engagement on learning interest. Global Edu Outlook 3:46–51
17.
Zurück zum Zitat Zhang J, Chen L (2019) Clustering-based undersampling with random over sampling examples and support vector machine for imbalanced classification of breast cancer diagnosis. Comput Assist Surgery 24:62–72 Zhang J, Chen L (2019) Clustering-based undersampling with random over sampling examples and support vector machine for imbalanced classification of breast cancer diagnosis. Comput Assist Surgery 24:62–72
18.
Zurück zum Zitat Zhao J, Jin J, Chen S et al (2020) A weighted hybrid ensemble method for classifying imbalanced data. Knowl Based Syst 203:106087CrossRef Zhao J, Jin J, Chen S et al (2020) A weighted hybrid ensemble method for classifying imbalanced data. Knowl Based Syst 203:106087CrossRef
19.
Zurück zum Zitat Chen J, Shen Y, Ali R (2018) Credit card fraud detection using sparse autoencoder and generative adversarial network. Electronics and Mobile Communication Conference, pp. 1054–1059 Chen J, Shen Y, Ali R (2018) Credit card fraud detection using sparse autoencoder and generative adversarial network. Electronics and Mobile Communication Conference, pp. 1054–1059
20.
Zurück zum Zitat Zaccagnino R, Capo C, Guarino A, et al (2021) Credit card fraud detection using sparse autoencoder and generative adversarial network. Multimedia Tools and Applications, pp. 15803–15824 Zaccagnino R, Capo C, Guarino A, et al (2021) Credit card fraud detection using sparse autoencoder and generative adversarial network. Multimedia Tools and Applications, pp. 15803–15824
21.
Zurück zum Zitat Guarino A, Lettieri N, Malandrino D, et al (2022) Adam or eve? Automatic users’ gender classification via gestures analysis on touch devices. Neural Computing and Applications, pp. 18473–18495 Guarino A, Lettieri N, Malandrino D, et al (2022) Adam or eve? Automatic users’ gender classification via gestures analysis on touch devices. Neural Computing and Applications, pp. 18473–18495
23.
Zurück zum Zitat Milojević S (2010) Power law distributions in information science: making the case for logarithmic binning. J Am Soc Information Sci Technol 61(12):2417–2425CrossRef Milojević S (2010) Power law distributions in information science: making the case for logarithmic binning. J Am Soc Information Sci Technol 61(12):2417–2425CrossRef
24.
Zurück zum Zitat Yang G, Ouyang Y, Ye Z, et al (2022) Social-path embedding-based transformer for graduation development prediction. Applied Intelligence, pp 1-18 Yang G, Ouyang Y, Ye Z, et al (2022) Social-path embedding-based transformer for graduation development prediction. Applied Intelligence, pp 1-18
25.
Zurück zum Zitat Zhao, T, Xiang Z, Wang S (2021) Graphsmote: Imbalanced node classification on graphs with graph neural networks. Proceedings of the 14th ACM international conference on web search and data mining, pp 833–841 Zhao, T, Xiang Z, Wang S (2021) Graphsmote: Imbalanced node classification on graphs with graph neural networks. Proceedings of the 14th ACM international conference on web search and data mining, pp 833–841
26.
Zurück zum Zitat Jin M, Zheng Y, Li Y F, et al (2021) Multi-scale contrastive siamese networks for self-supervised graph representation learning. In: proceedings of the thirtieth international joint conference on artificial intelligence, IJCAI-21, pp 1477–1483 Jin M, Zheng Y, Li Y F, et al (2021) Multi-scale contrastive siamese networks for self-supervised graph representation learning. In: proceedings of the thirtieth international joint conference on artificial intelligence, IJCAI-21, pp 1477–1483
27.
Zurück zum Zitat Chen X, He K (2021) Exploring simple siamese representation learning. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 15750–15758 Chen X, He K (2021) Exploring simple siamese representation learning. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 15750–15758
28.
Zurück zum Zitat Yang Z, Yang J, Rice K et al (2020) Using convolutional neural network to recognize learning images for early warning of at-risk students. IEEE Trans Learn Technol 13(3):617–630CrossRef Yang Z, Yang J, Rice K et al (2020) Using convolutional neural network to recognize learning images for early warning of at-risk students. IEEE Trans Learn Technol 13(3):617–630CrossRef
29.
Zurück zum Zitat Kong J, Han J, Ding J et al (2020) Analysis of students’ learning and psychological features by contrast frequent patterns mining on academic performance. Neural Comput Appl 32(1):205–211CrossRef Kong J, Han J, Ding J et al (2020) Analysis of students’ learning and psychological features by contrast frequent patterns mining on academic performance. Neural Comput Appl 32(1):205–211CrossRef
30.
Zurück zum Zitat Kabra RR, Bichkar RS (2011) Performance prediction of engineering students using decision trees. Int J Comput Appl 36(11):8–12 Kabra RR, Bichkar RS (2011) Performance prediction of engineering students using decision trees. Int J Comput Appl 36(11):8–12
31.
Zurück zum Zitat Chang H, Kim H (2021) Predicting the pass probability of secondary school students taking online classes. Comput Edu 164:104–110 Chang H, Kim H (2021) Predicting the pass probability of secondary school students taking online classes. Comput Edu 164:104–110
32.
Zurück zum Zitat Tadayon M, Pottie G (2020) Predicting student performance in an educational game using a hidden markov model. IEEE Trans Edu 63(4):299–304CrossRef Tadayon M, Pottie G (2020) Predicting student performance in an educational game using a hidden markov model. IEEE Trans Edu 63(4):299–304CrossRef
33.
Zurück zum Zitat Prabowo H, Hidayat A, Cenggoro T et al (2021) Aggregating time series and tabular data in deep learning model for university students’ gpa prediction. IEEE Access 9:87370–87377CrossRef Prabowo H, Hidayat A, Cenggoro T et al (2021) Aggregating time series and tabular data in deep learning model for university students’ gpa prediction. IEEE Access 9:87370–87377CrossRef
34.
Zurück zum Zitat Jiang Q, Zhao W, Zhao W et al (2017) Empirical research of predictive factors and intervention countermeasures of online learning performance on big data-based learning analytics. e-Edu Res 38(1):62–69 Jiang Q, Zhao W, Zhao W et al (2017) Empirical research of predictive factors and intervention countermeasures of online learning performance on big data-based learning analytics. e-Edu Res 38(1):62–69
35.
Zurück zum Zitat Wu K, Edwards A, Fan W, et al (2014) Classifying imbalanced data streams via dynamic feature group weighting with importance sampling. Proceedings of the 2014 SIAM international conference on data mining, pp 722–730 Wu K, Edwards A, Fan W, et al (2014) Classifying imbalanced data streams via dynamic feature group weighting with importance sampling. Proceedings of the 2014 SIAM international conference on data mining, pp 722–730
36.
Zurück zum Zitat Chawla NV, Bowyer KW, Hall LO et al (2002) SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 16:321–357CrossRef Chawla NV, Bowyer KW, Hall LO et al (2002) SMOTE: synthetic minority over-sampling technique. J Artif Intell Res 16:321–357CrossRef
37.
Zurück zum Zitat Ling CX, Sheng VS (2008) Cost-sensitive learning and the class imbalance problem. Encyclop Mach Learn 2011:231–235 Ling CX, Sheng VS (2008) Cost-sensitive learning and the class imbalance problem. Encyclop Mach Learn 2011:231–235
38.
Zurück zum Zitat Zhou ZH, Liu XY (2005) Training cost-sensitive neural networks with methods addressing the class imbalance problem. IEEE Trans Knowl Data Eng 18(1):63–77MathSciNetCrossRef Zhou ZH, Liu XY (2005) Training cost-sensitive neural networks with methods addressing the class imbalance problem. IEEE Trans Knowl Data Eng 18(1):63–77MathSciNetCrossRef
39.
Zurück zum Zitat He H, Garcia EA (2009) Learning from imbalanced data. IEEE Trans Knowl Data Eng 21(9):1263–1284CrossRef He H, Garcia EA (2009) Learning from imbalanced data. IEEE Trans Knowl Data Eng 21(9):1263–1284CrossRef
40.
Zurück zum Zitat LeCun Y, Bottou L, Bengio Y et al (1998) Gradient-based learning applied to document recognition. Proceed IEEE 86(11):2278–2324CrossRef LeCun Y, Bottou L, Bengio Y et al (1998) Gradient-based learning applied to document recognition. Proceed IEEE 86(11):2278–2324CrossRef
41.
Zurück zum Zitat Zhou F, Jin L, Dong J (2017) Review of convolutional neural network. Chin J Comput 40(6):1229–1251MathSciNet Zhou F, Jin L, Dong J (2017) Review of convolutional neural network. Chin J Comput 40(6):1229–1251MathSciNet
42.
Zurück zum Zitat Zhang S, Gong Y, Wang J (2019) The development of deep convolution neural network and its applications on computer vision. Chin J Comput 42(3):453–482MathSciNet Zhang S, Gong Y, Wang J (2019) The development of deep convolution neural network and its applications on computer vision. Chin J Comput 42(3):453–482MathSciNet
43.
Zurück zum Zitat Lawrence S, Giles CL, Tsoi AC et al (1997) Face recognition: a convolutional neural-network approach. IEEE Trans Neural Netw 8(1):98–113CrossRefPubMed Lawrence S, Giles CL, Tsoi AC et al (1997) Face recognition: a convolutional neural-network approach. IEEE Trans Neural Netw 8(1):98–113CrossRefPubMed
44.
Zurück zum Zitat Ciresan D C, Meier U, Masci J, et al (2011) Flexible, high performance convolutional neural networks for image classification. Twenty-second international joint conference on artificial intelligence Ciresan D C, Meier U, Masci J, et al (2011) Flexible, high performance convolutional neural networks for image classification. Twenty-second international joint conference on artificial intelligence
45.
Zurück zum Zitat Xu BB, Sham CT, Huang JJ, Shen HW, Cheng XQ (2020) A survey on graph convolutional neural network. Chin J Comput 43(5):755–780 Xu BB, Sham CT, Huang JJ, Shen HW, Cheng XQ (2020) A survey on graph convolutional neural network. Chin J Comput 43(5):755–780
46.
Zurück zum Zitat Lu M, Wang Y, Tan D et al (2021) Student program classification using gated graph attention neural network. IEEE Access 8:87857–87868CrossRef Lu M, Wang Y, Tan D et al (2021) Student program classification using gated graph attention neural network. IEEE Access 8:87857–87868CrossRef
47.
Zurück zum Zitat Zhang Y, Lu M, Zheng Y, Li HF (2021) Student grade prediction based on graph auto-encoder model. Comput Eng Appl 57(13):251–257 Zhang Y, Lu M, Zheng Y, Li HF (2021) Student grade prediction based on graph auto-encoder model. Comput Eng Appl 57(13):251–257
48.
Zurück zum Zitat You Y, Chen T, Sui Y et al (2020) Graph contrastive learning with augmentations. Adv Neural Information Process Syst 33:5812–5823 You Y, Chen T, Sui Y et al (2020) Graph contrastive learning with augmentations. Adv Neural Information Process Syst 33:5812–5823
49.
Zurück zum Zitat Chen T, Kornblith S, Norouzi M, et al (2020) A simple framework for contrastive learning of visual representations. International conference on machine learning, pp 1597–1607 Chen T, Kornblith S, Norouzi M, et al (2020) A simple framework for contrastive learning of visual representations. International conference on machine learning, pp 1597–1607
50.
Zurück zum Zitat More A S, Rana D P (2017) Review of random forest classification techniques to resolve data imbalance. 2017 1st International Conference on Intelligent Systems and Information Management (ICISIM), pp 72–78 More A S, Rana D P (2017) Review of random forest classification techniques to resolve data imbalance. 2017 1st International Conference on Intelligent Systems and Information Management (ICISIM), pp 72–78
51.
Zurück zum Zitat Da C, Xu S, Ding K, et al (2017) AMVH: Asymmetric multi-valued hashing. Proceedings of the IEEE conference on computer vision and pattern recognition, pp 736–744 Da C, Xu S, Ding K, et al (2017) AMVH: Asymmetric multi-valued hashing. Proceedings of the IEEE conference on computer vision and pattern recognition, pp 736–744
52.
Zurück zum Zitat Cao Y, Miao QG, Liu JC et al (2013) Advance and prospects of adaboost algorithm. Acta Autom Sin 39(6):745–758CrossRef Cao Y, Miao QG, Liu JC et al (2013) Advance and prospects of adaboost algorithm. Acta Autom Sin 39(6):745–758CrossRef
53.
Zurück zum Zitat Yang N (2019) Construction of artificial translation grading model based on BP neural network in college students’ translation grading system. J Intell Fuzzy Syst 37(5):6055–6062CrossRef Yang N (2019) Construction of artificial translation grading model based on BP neural network in college students’ translation grading system. J Intell Fuzzy Syst 37(5):6055–6062CrossRef
54.
Zurück zum Zitat Velickovic P, Cucurull G, Casanova A et al (2017) Graph attention networks. Stat 1050:20 Velickovic P, Cucurull G, Casanova A et al (2017) Graph attention networks. Stat 1050:20
55.
Zurück zum Zitat Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Computat 9(8):1735–1780CrossRef Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Computat 9(8):1735–1780CrossRef
56.
Zurück zum Zitat Wu J, Wang X, Feng F, et al (2021) Self-supervised graph learning for recommendation. Proceedings of the 44th international ACM SIGIR conference on research and development in information retrieval, pp 726-735 Wu J, Wang X, Feng F, et al (2021) Self-supervised graph learning for recommendation. Proceedings of the 44th international ACM SIGIR conference on research and development in information retrieval, pp 726-735
Metadaten
Titel
Multi-level contrastive graph learning for academic abnormality prediction
verfasst von
Yong Ouyang
Yuanlin Wang
Rong Gao
Yawen Zeng
Jinhang Liu
Zhiwei Ye
Publikationsdatum
06.12.2023
Verlag
Springer London
Erschienen in
Neural Computing and Applications / Ausgabe 7/2024
Print ISSN: 0941-0643
Elektronische ISSN: 1433-3058
DOI
https://doi.org/10.1007/s00521-023-09268-4

Weitere Artikel der Ausgabe 7/2024

Neural Computing and Applications 7/2024 Zur Ausgabe