To address the limitations of inaccuracy and data fragmentation in educational assessment systems, this study proposes a novel computational framework integrating federated learning (FL) with knowledge distillation. By modelling students as edge clients and institutional servers as central aggregators, the framework enables distributed collaborative training while preserving data privacy. Crucially, we optimize the FL aggregation strategy through a hierarchical knowledge distillation mechanism, where local models are guided by distilled global knowledge to enhance parameter efficiency. Experimental validation demonstrates a 10.3% improvement in assessment accuracy compared to baseline methods, alongside a 17% reduction in communication overhead. The proposed model showcases scalable computational efficiency for large-scale educational data analysis, with potential applications extending to scientific data fusion scenarios in IoT and edge computing environments.
Ejsing-DuunSPischetolaM. Does it matter?’: learning through aesthetic experiences in a higher education communication design course. Postdigit Sci Educ2023; 5: 799–822.
2.
WangM. Analyzing the influence of college aesthetic education teaching on college students’ innovation ability and artistic literacy based on decision tree classification model. Mob Inf Syst2022; 2022: 9587049.
3.
ZhangCXieYBaiH, et al.A survey on federated learning. Knowl Base Syst2021; 216: 11–19.
4.
GossH. Student learning outcomes assessment in higher education and in academic libraries: a review of the literature. J Acad Librarian2022; 48: 24–39.
5.
AliL. The design of curriculum, assessment and evaluation in higher education with constructive alignment. J Educ E-learn Res2018; 5: 72–78.
6.
VanLehnKMartinJ. Evaluation of an assessment system based on Bayesian student modeling. Int J Artif Intell Educ1998; 8: 179–221.
7.
GuY. Exploring the application of teaching evaluation models incorporating association rules and weighted naive Bayesian algorithms. Intell Syst Appl2023; 20: 200297.
8.
JeongY-SChoN-W. Evaluation of e-learners’ concentration using recurrent neural networks. J Supercomput2023; 79: 4146–4163.
9.
AljaloudASUliyanDMAlkhalilA, et al.A deep learning model to predict student learning outcomes in LMS using CNN and LSTM. IEEE Access2022; 10: 85255–85265.
10.
ZhangHWangLQuY, et al.Enhanced dynamic key-value memory networks for personalized student modeling and learning ability classification. Cognit Comput2024; 16: 2878–2901.
11.
ZhangJTangZXieY, et al.Timed key-value memory network for flotation reagent control. Control Eng Pract2020; 98: 51–63.
12.
FuEYNgaiGLeongHV, et al.Using attention-based neural networks for predicting student learning outcomes in service-learning. Educ Inf Technol2023; 28: 13763–13789.
13.
VenkateshwarluGSireeshaGReddyBP, et al.Transformer-based adaptive examination systems for scalable, accurate, and personalized assessments in education. Frontiers in Collaborative Research2024; 2: 10–19.
14.
Gerritsen-van LeeuwenkampKJJoosten-Ten BrinkeDKesterL. Students’ perceptions of assessment quality related to their learning approaches and learning outcomes. Stud Educ Eval2019; 63: 72–82.
15.
StennerAJFisherJWPStoneMH, et al.Causal rasch models. Front Psychol2013; 4: 536.
16.
ChenYWeiGLiuJ, et al.A prediction model of student performance based on self-attention mechanism. Knowl Inf Syst2023; 65: 733–758.
17.
Al-AzaziFAGhurabMAnn-Lstm. A deep learning model for early student performance prediction in MOOC. Heliyon2023; 9: 31–45.
18.
AlshmranyS. Adaptive learning style prediction in e-learning environment using levy flight distribution based CNN model. Clust Comput2022; 25: 523–536.
19.
ZhangYLiYWangY, et al.Federated learning-outcome prediction with multi-layer privacy protection. Front Comput Sci2024; 18: 11–37.
20.
ZhangTLiuHTaoJ, et al.Enhancing dropout prediction in distributed educational data using learning pattern awareness: a federated learning approach. Mathematics2023; 11: 49–52.
21.
ChuY-WHosseinalipourSTenorioE, et al.Multi-layer personalized federated learning for mitigating biases in student predictive analytics. IEEE Transactions on Emerging Topics in Computing2024; 7: 1–15.
22.
FarooqUNaseemSMahmoodT, et al.Transforming educational insights: strategic integration of federated learning for enhanced prediction of student learning outcomes. J Supercomput2024; 80: 16334–16367.
23.
JiSTanYSaravirtaT, et al.Emerging trends in federated learning: from model fusion to federated x learning. Int J Mach Learn Cybern2024; 15: 3769–3790.
24.
WeiKLiJDingM, et al.Federated learning with differential privacy: algorithms and performance analysis. IEEE Trans Inf Forensics Secur2020; 15: 3454–3469.
25.
GhoshAChungJYinD, et al.An efficient framework for clustered federated learning. Adv Neural Inf Process Syst2020; 33: 19586–19597.
26.
PillutlaKKakadeSMHarchaouiZ. Robust aggregation for federated learning. IEEE Trans Signal Process2022; 70: 1142–1154.
27.
AlkhulaifiAAlsahliFAhmadI. Knowledge distillation in deep learning and its applications. PeerJ Comput Sci2021; 7: e474.
28.
JavedSMahmoodAQaiserT, et al.Knowledge distillation in histology landscape by multi-layer features supervision. IEEE J Biomed Health Inform2023; 27: 2037–2046.
29.
LvJYangHLiP. Wasserstein distance rivals kullback-leibler divergence for knowledge distillation. Adv Neural Inf Process Syst2024; 37: 65445–65475.
