47,858 Hits in 7.9 sec

A Survey of Knowledge Tracing [article]

Qi Liu, Shuanghong Shen, Zhenya Huang, Enhong Chen, Yonghe Zheng
2021 arXiv   pre-print
Knowledge Tracing (KT), which aims to monitor students' evolving knowledge state, is a fundamental and crucial task to support these intelligent services.  ...  Finally, we provide some potential directions for future research in this fast-growing field.  ...  [22] logistic regression independent the output of logistic regression function performance factor analysis [23] knowledge tracing machines [32] factorization machines Deep learning-based models  ... 
arXiv:2105.15106v2 fatcat:723wl2krqzd3ziboc2vmhdu23q

On Overfitting and Asymptotic Bias in Batch Reinforcement Learning with Partial Observability (Extended Abstract)

Vincent Francois-Lavet, Guillaume Rabusseau, Joelle Pineau, Damien Ernst, Raphael Fonteneau
2020 Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence  
data) and a term due to overfitting (additional suboptimality due to limited data).  ...  In the context of reinforcement learning with partial observability, this paper provides an analysis of the tradeoff between these two error sources.  ...  They studied the parameterizations for handling the ordinal nature of ratings, and presented the integration of multiple Boltzmann machines for user-based and item-based processes. Wang et al.  ... 
doi:10.24963/ijcai.2020/695 dblp:conf/ijcai/0001Z20 fatcat:yx2wihhuobgmjjh4aevkbr33g4

Multiple Features Fusion Attention Mechanism Enhanced Deep Knowledge Tracing for Student Performance Prediction

Dong Liu, Yunping Zhang, Jun Zhang, Qinpeng Li, Congpin Zhang, Yu Yin
2020 IEEE Access  
the knowledge tracing model.  ...  Generally, student performance prediction is achieved by tracing the evolution of each student's knowledge states via a series of learning activities.  ...  RELATED WORK At present, student performance prediction approaches can be classified into three main categories: cognitive diagnosis, knowledge tracing and deep learning.  ... 
doi:10.1109/access.2020.3033200 fatcat:oyov7avxjnaktksdc36bg2cgxy

Research Commentary on Recommendations with Side Information: A Survey and Research Directions [article]

Zhu Sun, Qing Guo, Jie Yang, Hui Fang, Guibing Guo, Jie Zhang, Robin Burke
2019 arXiv   pre-print
One involves the different methodologies of recommendation: the memory-based methods, latent factor, representation learning, and deep learning models.  ...  The others cover different representations of side information, including structural data (flat, network, and hierarchical features, and knowledge graphs); and non-structural data (text, image and video  ...  We also gratefully acknowledge the support of National Natural Science Foundation of China (Grant No. 71601104, 71601116, 71771141 and 61702084) and the support of the Fundamental Research Funds for the  ... 
arXiv:1909.12807v2 fatcat:2nj4crzcd5attidhd3kneszmki

A review of drug knowledge discovery using BioNLP and tensor or matrix decomposition

Mina Gachloo, Yuxing Wang, Jingbo Xia
2019 Genomics & Informatics  
Prediction of the relations among drug and other molecular or social entities is the main knowledge discovery pattern for the purpose of drug-related knowledge discovery.  ...  Computational approaches have combined the information from different sources and levels for drug-related knowledge discovery, which provides a sophisticated comprehension of the relationship among drugs  ...  Kevin Bretonnel Cohen for many interesting discussions and nice suggestions about the paper, as well as Dr. Jin-Dong Kim for many illuminative discussions during the BLAH5 workshop.  ... 
doi:10.5808/gi.2019.17.2.e18 pmid:31307133 pmcid:PMC6808632 fatcat:w65sf7kkevflneg4marbtnmw6m

Recommender systems based on graph embedding techniques: A review

Yue Deng
2022 IEEE Access  
As the focus, this article systematically retrospects graph embedding-based recommendation from embedding techniques for bipartite graphs, general graphs and knowledge graphs, and proposes a general design  ...  As for alleviating the sparsity and cold start problems encountered by recommender systems, researchers generally resort to employing side information or knowledge in recommendation as a strategy for uncovering  ...  ACKNOWLEDGEMENTS The author acknowledges Linyuan Lü, Shuqi Xu, Xu Na, Hao Wang and Honglei Zhang for their discussions and suggestions.  ... 
doi:10.1109/access.2022.3174197 fatcat:s267xaasovh6ffaomi7l32pqyi

Deep Knowledge Tracing Based on Spatial and Temporal Representation Learning for Learning Performance Prediction

Liting Lyu, Zhifeng Wang, Haihong Yun, Zexue Yang, Ya Li
2022 Applied Sciences  
To adequately mine features of students' learning process, Deep Knowledge Tracing Based on Spatial and Temporal Deep Representation Learning for Learning Performance Prediction (DKT-STDRL) is proposed  ...  Knowledge tracing (KT) serves as a primary part of intelligent education systems.  ...  A new KT model is proposed by us, which is called Deep Knowledge Tracing Based on Spatial and Temporal Deep Representation Learning for Learning Performance Prediction (DKT-STDRL).  ... 
doi:10.3390/app12147188 fatcat:mllasvaou5au5n6cbuhrgaqys4

Deep Graph Memory Networks for Forgetting-Robust Knowledge Tracing [article]

Ghodai Abdelrahman, Qing Wang
2021 arXiv   pre-print
Tracing a student's knowledge is vital for tailoring the learning experience.  ...  To address these challenges, in this paper, we propose a novel knowledge tracing model, namely Deep Graph Memory Network (DGMN).  ...  These attempts can be generally categorized into three main categories: 1) Bayesian methods, 2) deep learning methods, and 3) graph-based methods.  ... 
arXiv:2108.08105v1 fatcat:a6wj7dkifnhwxprismlqsea464

Study-GNN: A Novel Pipeline for Student Performance Prediction Based on Multi-Topology Graph Neural Networks

Ming Li, Xiangru Wang, Yi Wang, Yuting Chen, Yixuan Chen
2022 Sustainability  
In particular, we propose various ways for graph construction based on similarity learning using different distance metrics.  ...  In this paper, we use graph structure to reflect the students' relationships and propose a novel pipeline for student performance prediction based on newly-developed multi-topology graph neural networks  ...  [33] proposed a graph-based knowledge tracing enhanced cognitive diagnosis model (GKT-CD) and improved the performance of cognitive diagnostics for both the student factor and exercise factor.  ... 
doi:10.3390/su14137965 fatcat:ngclyafzq5cvnd7ne5jvqmh2oe

Domain Adaption for Knowledge Tracing [article]

Song Cheng, Qi Liu, Enhong Chen
2020 arXiv   pre-print
Specifically, for the first aspect, we incorporate the educational characteristics (e.g., slip, guess, question texts) based on the deep knowledge tracing (DKT) to obtain a good performed knowledge tracing  ...  Extensive experimental results on two private datasets and seven public datasets clearly prove the effectiveness of AKT for great knowledge tracing performance and its superior transferable ability.  ...  As for the deep approaches, deep knowledge tracing (DKT) [30] is the first deep learning based method, which outperforms all of the conventional methods because of its nonlinear input-to-state and state-to-state  ... 
arXiv:2001.04841v1 fatcat:f3nbczzg2nb6hpp5m7d3ygd3iy

Dynamic Intention-Aware Recommendation System [article]

Shuai Zhang, Lina Yao
2017 arXiv   pre-print
Compare to prior work, our proposal possesses the following advantages: (1) it takes user intentions and demands into account through intention mining techniques.  ...  By unearthing user intentions from the historical user-item interactions, and various user digital traces harvested from social media and Internet of Things, it is capable of delivering more satisfactory  ...  To learn the shared representations, we mainly investigated two techniques: Multi-Task Learning and Multimodal Deep Learning.  ... 
arXiv:1703.03112v2 fatcat:af3jq4emcna6heoyujwxwqdmgu

Empirical Evaluation of Deep Learning Models for Knowledge Tracing: Of Hyperparameters and Metrics on Performance and Replicability [article]

Sami Sarsa, Juho Leinonen, Arto Hellas
2022 arXiv   pre-print
We review and evaluate a body of deep learning knowledge tracing (DLKT) models with openly available and widely-used data sets, and with a novel data set of students learning to program.  ...  As baselines, we evaluate simple non-learning models, logistic regression and Bayesian Knowledge Tracing (BKT).  ...  We are grateful for the grant by the Media Industry Research Foundation of Finland which partially funded this work. We thank the reviewers for their valuable comments that helped improved this  ... 
arXiv:2112.15072v4 fatcat:i6pkahldsnbmxn45zpvtyk5zf4

Entity-Enhanced Graph Convolutional Network for Accurate and Explainable Recommendation

Qinqin Wang, Elias Tragos, Neil Hurley, Barry Smyth, Aonghus Lawlor, Ruihai Dong
2022 Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization  
Side information should be taken into account to improve performance.  ...  Based on our study, we propose that in the hybrid structure of the KG, its rich relationships are an essential factor for successful recommendation from both an explanation and performance perspective.  ...  We require user-entity interaction data for both training and explanation.  ... 
doi:10.1145/3503252.3531316 fatcat:vyys7qsfxfdabisqnjohegg3ry

Making Efficient Use of a Domain Expert's Time in Relation Extraction [article]

Linara Adilova, Sven Giesselbach, Stefan Rüping
2018 arXiv   pre-print
We introduce an active learning based extension, that allows our neural network to incorporate expert feedback and report on first results on a complex data set.  ...  Distant supervision provides a mean of labeling data given known relations in a knowledge base, but it suffers from noisy labeling.  ...  Acknowledgements: This work upon which this paper is based was supported by means of the Bundesministerium für Bildung und Forschung (Förderkennzeichen 031L0025C).  ... 
arXiv:1807.04687v1 fatcat:xalliyi3wvhzbijxi3jwi77ty4

What's happened in MOOC Posts Analysis, Knowledge Tracing and Peer Feedbacks? A Review [article]

Manikandan Ravikiran
2020 arXiv   pre-print
learning content is managed and learning activities are organised (Stone and Zheng,2014) and latter focusing on using data mining techniques for the analysis of data so generated.  ...  Learning Management Systems (LMS) and Educational Data Mining (EDM) are two important parts of online educational environment with the former being a centralised web-based information systems where the  ...  LITERATURE REVIEW The literature review is divided into three parts namely reviews of MOOC Post analysis, Knowledge Tracing and Peer Feedbacks.  ... 
arXiv:2001.09830v1 fatcat:fwxjsrusfncjjpv4vdrglm4s2m
« Previous Showing results 1 — 15 out of 47,858 results