相关参考文献
注意：仅列出部分参考文献，下载原文获取全部文献信息。
Article
Computer Science, Artificial Intelligence
Pratik Mazumder et al.
Summary: This study proposes a novel approach to mitigate bias in an image classification model in a limited data setting. Experimental results demonstrate that the proposed method significantly reduces the model bias score and improves the model performance.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
WenWu Wang et al.
Summary: In the era of big data, we propose different regression models (asymmetric local polynomial regression, symmetric local constant regression, and one-sided local linear forecasting) to model the change rate of data. Through asymptotic analysis and kernel function derivation, we establish the asymptotic properties of the estimators and propose debiased estimators to reduce estimation bias for highly-oscillatory functions. We also propose a data-driven two-step procedure for simultaneous model selection and tuning parameter selection. Simulation studies and real data examples demonstrate the usefulness of our proposed estimators.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Xiaoge Zhang et al.
Summary: This paper presents a framework based on uncertainty quantification to enhance the interpretability of deep learning models. By propagating uncertainty to model predictions and optimizing pixels using entropy and differential evolution, the model interpretability is effectively improved.
KNOWLEDGE-BASED SYSTEMS
(2022)
Review
Computer Science, Artificial Intelligence
Sonia Farhana Nimmy et al.
Summary: This paper emphasizes the importance of managing operational disruptions for the success of supply chain operations and the necessity of using explainable AI methods to manage operational risks. The research also highlights the shortcomings of current techniques and provides inspiration for future research directions.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Guotong Xue et al.
Summary: With the increasing evolution of real world networks, such as social networks and user-item networks, dynamic network embedding has gained significant research attention in recent years. This paper provides a survey on the data models, representation learning techniques, evaluation, and applications of dynamic network embedding, and identifies common patterns from current related works.
Article
Computer Science, Artificial Intelligence
Ping Xuan et al.
Summary: This study proposes a novel dynamic graph convolution autoencoder with node-attribute-wise attention for relation inference and reasoning, applied in kidney and tumor segmentation. The experimental results demonstrate the effectiveness of this approach, particularly in dealing with objects with weak boundaries, irregular shapes, and various sizes.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Yael Mathov et al.
Summary: Recent work on adversarial learning has mainly focused on neural networks and domains in which those networks excel. This study argues that machine learning models trained on heterogeneous tabular data are as susceptible to adversarial manipulations as those trained on continuous or homogeneous data. It introduces a generic optimization framework for identifying adversarial perturbations in heterogeneous input spaces and demonstrates its effectiveness on different content domains.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Xiangyu Song et al.
Summary: The goal of Knowledge Tracing is to estimate students' mastery of a concept based on their learning history. With the rise of deep learning, Deep Knowledge Tracing has shown success in organizing students' learning plans.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Mingbo Zhao et al.
Summary: This paper proposes a sub-graph based on fixed anchors to solve the problem of inability to extend or update the graph in Manifold Ranking methods. This method can update the graph more easily and predict ranking scores for the whole data through an efficient graph regularization framework.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Information Systems
Xiangyu Song et al.
Summary: Knowledge Tracing (KT) aims to track students' mastery of knowledge based on their historical learning interactions. To address the shortcomings of existing methods, a deep Knowledge Tracing framework called JKT is proposed, which utilizes a Joint graph convolutional network to model multi-dimensional relationships and improve interpretability.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
Xiulin Zheng et al.
Summary: Mining non-stationary streams poses challenges due to their infinite length, dynamic characteristics, concept drift, concept evolution, and limited labeled data. Existing supervised methods may result in poor performance and efficiency in the presence of scarce labeled data. This paper proposes a semi-supervised framework ESCR to detect recurring concept drifts and concept evolution in data streams with partially labeled data. The framework utilizes clustering-based classifiers, Jensen-Shannon divergence for change detection, and outlier monitoring for concept evolution, while also improving efficiency through recursive function and dynamic programming. Extensive experiments show the effectiveness and efficiency of ESCR compared to other semi-supervised methods.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Boyan Wang et al.
Summary: The paper proposes a unified framework, Hierarchical Cognitive Structure Learning Model (HCSM), for handling hierarchical multi-label text classification (HMLTC) tasks. This model comprehensively utilizes partial new knowledge and global hierarchical label structure, demonstrating superior performance in experimental results on four benchmark datasets.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Tomaz Stepisnik et al.
Summary: This paper introduces oblique predictive clustering trees to address the limitations of standard predictive clustering trees in high-dimensional output spaces and sparse data. By designing and implementing methods for learning oblique splits, the resulting oblique trees are capable of efficiently handling high-dimensional data and exploiting sparse data.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Theory & Methods
Xinyi Zhou et al.
ACM COMPUTING SURVEYS
(2020)
Article
Computer Science, Artificial Intelligence
Wensheng Gan et al.
KNOWLEDGE-BASED SYSTEMS
(2018)
Article
Multidisciplinary Sciences
Soroush Vosoughi et al.
Article
Computer Science, Hardware & Architecture
Yuanyuan Zhu et al.
