Abstract
Graph embedding (GE) aims to acquire low-dimensional node representations while maintaining the graph’s structural and semantic attributes. Intelligent tutoring systems (ITS) signify a noteworthy achievement in the fusion of AI and education. Utilizing GE to model ITS can elevate their performance in predictive and annotation tasks. Current GE techniques, whether applied to heterogeneous or dynamic graphs, struggle to efficiently model ITS data. The GEs within ITS should retain their semidynamic, independent, and smooth characteristics. This article introduces a heterogeneous evolution network (HEN) for illustrating entities and relations within an ITS. Additionally, we introduce a temporal extension graph neural network (TEGNN) to model both evolving and static nodes within the HEN. In the TEGNN framework, dynamic nodes are initially improved over time through temporal extension (TE), providing an accurate depiction of each learner’s implicit state at each time step. Subsequently, we propose a stochastic temporal pooling (STP) strategy to estimate the embedding sets of all evolving nodes. This effectively enhances model efficiency and usability. Following this, a heterogeneous aggregation network is devised to proficiently extract heterogeneous features from the HEN. This network employs both node-level and relation-level attention mechanisms to craft aggregated node features. To emphasize the superiority of TEGNN, we perform experiments on several real ITS datasets and show that our method significantly outperforms the state-of-the-art approaches. The experiments validate that TE serves as an efficient framework for modeling temporal information in GE, and STP not only accelerates the training process but also enhances the resultant accuracy.
- [1] . 2018. Automatically learning topics and difficulty levels of problems in online judge systems. ACM Trans. Inf. Syst. 36, 3, Article
27 (Mar. 2018), 33 pages.DOI: Google ScholarDigital Library - [2] . 2023. A systematic review of intelligent tutoring systems based on Gross body movement detected using computer vision. Comput. Educ.: Artif. Intell. 4 (2023), 100125.
DOI: Google ScholarCross Ref - [3] . 2018. Fuzzy cognitive diagnosis for modelling examinee performance. ACM Trans. Intell. Syst. Technol. 9, 4, Article
48 (Jan. 2018), 26 pages.DOI: Google ScholarDigital Library - [4] . 2022. Deep cognitive diagnosis model for predicting students’ performance. Fut. Gener. Comput. Syst. 126 (2022), 252–262.
DOI: Google ScholarDigital Library - [5] . 2015. Deep knowledge tracing. In Advances in Neural Information Processing Systems, , , , , and (Eds.), Vol. 28. Curran Associates, Inc.Google Scholar
- [6] . 2021. EKT: Exercise-aware knowledge tracing for student performance prediction. IEEE Trans. Knowl. Data Eng. 33, 1 (2021), 100–115.
DOI: Google ScholarDigital Library - [7] . 2020. Learning or forgetting? A dynamic approach for tracking the knowledge proficiency of students. ACM Trans. Inf. Syst. 38, 2, Article
19 (Feb. 2020), 33 pages.DOI: Google ScholarDigital Library - [8] . 2021. A survey of knowledge tracing. arXiv:2105.15106. Retrieved from https://arxiv.org/abs/2105.15106Google Scholar
- [9] . 2022. Ensemble knowledge tracing: Modeling interactions in learning process. Expert Syst. Appl. 207 (2022), 117680.
DOI: Google ScholarDigital Library - [10] . 2022. Ability boosted knowledge tracing. Inf. Sci. 596 (2022), 567–587.
DOI: Google ScholarDigital Library - [11] . 2019. Exploiting cognitive structure for adaptive learning. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery; Data Mining (KDD’19). Association for Computing Machinery, New York, NY, 627–635.
DOI: Google ScholarDigital Library - [12] . 2018. Time and location aware points of interest recommendation in location-based social networks. J. Comput. Sci. Technol. 33 (2018), 1219–1230.Google ScholarCross Ref
- [13] . 2019. Ontology-enhanced educational annotation activities. Sustainability 11, 16 (2019).
DOI: Google ScholarCross Ref - [14] . 2019. Student performance prediction and classification using machine learning algorithms. In Proceedings of the 8th International Conference on Educational and Information Technology (ICEIT’19). Association for Computing Machinery, New York, NY, 7–11.
DOI: Google ScholarDigital Library - [15] . 2021. Student performance prediction based on blended learning. IEEE Trans. Educ. 64, 1 (2021), 66–73.
DOI: Google ScholarCross Ref - [16] . 2022. Evaluation of split-and-rephrase output of the knowledge extraction tool in the intelligent tutoring system. Expert Syst. Appl. 187 (2022), 115900.
DOI: Google ScholarCross Ref - [17] . 2023. ICD: A new interpretable cognitive diagnosis model for intelligent tutor systems. Expert Syst. Appl. 215 (2023), 119309.
DOI: Google ScholarDigital Library - [18] . 2009. Evolution of biomolecular networks–lessons from metabolic and protein interactions. Nat. Rev. Molec. Cell Biol. 10, 11 (2009), 791–803.Google ScholarCross Ref
- [19] . 2008. Statistical properties of community structure in large social and information networks. In Proceedings of the 17th International Conference on World Wide Web (WWW’08). Association for Computing Machinery, New York, NY, 695–704.
DOI: Google ScholarDigital Library - [20] . 2022. A survey on knowledge graphs: Representation, acquisition, and applications. IEEE Trans. Neural Netw. Learn. Syst. 33, 2 (2022), 494–514.
DOI: Google ScholarCross Ref - [21] . 2021. HGAT: Heterogeneous graph attention networks for semi-supervised short text classification. ACM Trans. Inf. Syst. 39, 3, Article
32 (May 2021), 29 pages.DOI: Google ScholarDigital Library - [22] . 2018. Graph embedding techniques, applications, and performance: A survey. Knowl.-Bas. Syst. 151 (2018), 78–94.
DOI: Google ScholarCross Ref - [23] . 2019. Heterogeneous graph attention network. In Proceedings of the World Wide Web Conference (WWW’19). Association for Computing Machinery, New York, NY, 2022–2032.
DOI: Google ScholarDigital Library - [24] . 2020. EvolveGCN: Evolving graph convolutional networks for dynamic graphs. Proceedings of the AAAI Conference on Artificial Intelligence 34, 04 (
Apr. 2020), 5363–5370.DOI: Google ScholarCross Ref - [25] . 2022. Neural temporal walks: Motif-aware representation learning on continuous-time dynamic graphs. In Advances in Neural Information Processing Systems, , , , and (Eds.).Google Scholar
- [26] . 2011. How to grow a mind: Statistics, structure, and abstraction. Science 331, 6022 (2011), 1279–1285.Google ScholarCross Ref
- [27] . 2011. The critical role of retrieval practice in long-term retention. Trends Cogn. Sci. 15, 1 (2011), 20–27.Google ScholarCross Ref
- [28] . 2008. The critical importance of retrieval for learning. Science 319, 5865 (2008), 966–968.Google ScholarCross Ref
- [29] . 2018. Addressing two problems in deep knowledge tracing via prediction-consistent regularization. In Proceedings of the fth Annual ACM Conference on Learning at Scale (L@S’18). Association for Computing Machinery, New York, NY, Article
5 , 10 pages.DOI: Google ScholarDigital Library - [30] . 2013. Distributed large-scale natural graph factorization. In Proceedings of the 22nd International Conference on World Wide Web (WWW’13). Association for Computing Machinery, New York, NY, 37–48.
DOI: Google ScholarDigital Library - [31] . 2016. Asymmetric transitivity preserving graph embedding. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’16). Association for Computing Machinery, New York, NY, 1105–1114.
DOI: Google ScholarDigital Library - [32] . 2014. DeepWalk: Online learning of social representations. In Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’14). Association for Computing Machinery, New York, NY, 701–710.
DOI: Google ScholarDigital Library - [33] . 2016. Node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’16). Association for Computing Machinery, New York, NY, 855–864.
DOI: Google ScholarDigital Library - [34] . 2016. Semi-supervised classification with graph convolutional networks. arXiv:1609.02907. Retrieved from https://arxiv.org/abs/1609.02907Google Scholar
- [35] . 2017. Graph attention networks. Stat 1050, 20 (2017), 10–48550.Google Scholar
- [36] . 2017. Inductive representation learning on large graphs. In Advances in Neural Information Processing Systems, , , , , , , and (Eds.), Vol. 30. Curran Associates, Inc.Google Scholar
- [37] . 2023. A survey on heterogeneous graph embedding: Methods, techniques, applications and sources. IEEE Trans. Big Data 9, 2 (2023), 415–436.
DOI: Google ScholarCross Ref - [38] . 2017. Metapath2vec: Scalable representation learning for heterogeneous networks. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’17). Association for Computing Machinery, New York, NY, 135–144.
DOI: Google ScholarDigital Library - [39] . 2019. Heterogeneous information network embedding for recommendation. IEEE Trans. Knowl. Data Eng. 31, 2 (2019), 357–370.
DOI: Google ScholarDigital Library - [40] . 2018. PME: Projected metric embedding on heterogeneous networks for link prediction. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery; Data Mining (KDD’18). Association for Computing Machinery, New York, NY, 1177–1186.
DOI: Google ScholarDigital Library - [41] . 2019. Relation structure-aware heterogeneous information network embedding. Proceedings of the AAAI Conference on Artificial Intelligence 33, 01 (
Jul. 2019), 4456–4463.DOI: Google ScholarDigital Library - [42] . 2022. GraphHINGE: Learning interaction models of structured neighborhood on heterogeneous information network. ACM Trans. Inf. Syst. 40, 3, Article
45 (Mar. 2022), 35 pages.DOI: Google ScholarDigital Library - [43] . 2021. PGRA: Projected graph relation-feature attention network for heterogeneous information network embedding. Inf. Sci. 570 (2021), 769–794.
DOI: Google ScholarDigital Library - [44] . 2016. Scalable temporal latent space inference for link prediction in dynamic social networks. IEEE Trans. Knowl. Data Eng. 28, 10 (2016), 2765–2777.
DOI: Google ScholarDigital Library - [45] . 2017. Attributed network embedding for learning in a dynamic environment. In Proceedings of the ACM on Conference on Information and Knowledge Management (CIKM’17). Association for Computing Machinery, New York, NY, 387–396.
DOI: Google ScholarDigital Library - [46] . 2017. Link prediction with spatial and temporal consistency in dynamic networks. In Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI’17). 3343–3349.Google ScholarCross Ref
- [47] . 2019. Dyn2Vec: Exploiting dynamic behaviour using difference networks-based node embeddings for classification. In Proceedings of the International Conference on Data Science. CSREA Press, 194–200.Google Scholar
- [48] . 2019. Node embedding over temporal graphs. arXiv:1903.08889. Retrieved from https://arxiv.org/abs/1903.08889Google Scholar
- [49] . 2019. Dynamic network embedding by semantic evolution. In Proceedings of the International Joint Conference on Neural Networks (IJCNN’19). 1–8.
DOI: Google ScholarCross Ref - [50] . 2022. A novel representation learning for dynamic graphs based on graph convolutional networks. IEEE Trans. Cybernet. (2022), 1–14.
DOI: Google ScholarCross Ref - [51] . 2021. Learning and updating node embedding on dynamic heterogeneous information network. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining (WSDM’21). Association for Computing Machinery, New York, NY, 184–192.
DOI: Google ScholarDigital Library - [52] . 2022. Heterogeneous temporal graph neural network. Proceedings of the SIAM International Conference on Data Mining (SDM’22), 657–665.Google ScholarCross Ref
- [53] . 2013. Distributed representations of words and phrases and their compositionality. In Advances in Neural Information Processing Systems, , , , , and (Eds.), Vol. 26. Curran Associates, Inc.Google ScholarDigital Library
- [54] . 2009. Addressing the assessment challenge with an online system that tutors as it assesses. User Model. User-adapt. Interact. 19, 3 (2009), 243–266.Google ScholarDigital Library
- [55] . 2020. Ednet: A large-scale hierarchical dataset in education. In Proceedings of the 21st International Conference on Artificial Intelligence in Education (AIED’20). Springer, 69–73.Google ScholarDigital Library
- [56] . 2015. Modeling exercise relationships in E-Learning: A unified approach. In Proceedings of the International Conference on Educational Data Mining (EDM’15). 532–535.Google Scholar
- [57] . 2017. Graph attention networks. Stat 1050, 20 (2017), 10–48550.Google Scholar
- [58] . 2021. A broader picture of random-walk based graph embedding. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD’21). Association for Computing Machinery, New York, NY, 685–695.
DOI: Google ScholarDigital Library - [59] . 2013. Translating embeddings for modeling multi-relational data. In Advances in Neural Information Processing Systems, , , , , and (Eds.), Vol. 26. Curran Associates, Inc. https://proceedings.neurips.cc/paper_files/paper/2013/file/1cecc7a77928ca8133fa24680a88d2f9-Paper.pdfGoogle Scholar
- [60] . 2014. Embedding entities and relations for learning and inference in knowledge bases. arXiv:1412.6575. Retrieved from https://arxiv.org/bs/1412.6575Google Scholar
- [61] . 2022. How does knowledge graph embedding extrapolate to unseen data: A semantic evidence view. In Proceedings of the AAAI Conference on Artificial Intelligence, 5781–5791.
DOI: Google ScholarCross Ref - [62] . 2018. Dynamic graph representation learning via self-attention networks. arXiv:1812.09430. Retrieved from https://arxiv.org/abs/1812.09430Google Scholar
- [63] . 2020. Temporal graph networks for deep learning on dynamic graphs. arXiv:2006.10637. Retrieved from https://arxiv.org/abs/2006.10637Google Scholar
Index Terms
- Heterogeneous Evolution Network Embedding with Temporal Extension for Intelligent Tutoring Systems
Recommendations
Cluster-Aware Heterogeneous Information Network Embedding
WSDM '22: Proceedings of the Fifteenth ACM International Conference on Web Search and Data MiningHeterogeneous Information Network (HIN) embedding refers to the low-dimensional projections of the HIN nodes that preserve the HIN structure and semantics. HIN embedding has emerged as a promising research field for network analysis as it enables ...
Reducing uncertainty of dynamic heterogeneous information networks: a fusing reconstructing approach
In real world, a heterogeneous information network (HIN) is often dynamic due to the time varying features of the nodes, and uncertain due to missing values and noise. In this paper, we investigate the problem of reducing the uncertainty of a dynamic HIN,...
ABLE: Meta-Path Prediction in Heterogeneous Information Networks
Given a heterogeneous information network (HIN) H, a head node h, a meta-path P, and a tail node t, the meta-path prediction aims at predicting whether h can be linked to t by an instance of P. Most existing solutions either require predefined meta-paths, ...
Comments