Scalable Semi-Supervised Learning by Efficient Anchor Graph Regularization

By Meng Wang, Weijie Fu, Shijie Hao, Dacheng Tao, Xindong Wu. 2016

220 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Neural Collaborative Filtering (2017, methodology): “To learn model parameters, existing pointwise methods [14, 39] largely perform a regression with squared loss:”
Multiview Spectral Clustering via Structured Low-Rank Matrix Factorization (2017, methodology): “Here, we follow the assumption in [39] to see ki as the cluster number of data objects within the i th view, and the data-cluster symmetric matrix factorization has been widely adopted by the numerous existing research, including semisupervised learning [40], [41], metric fusion [19], and clustering”
Structured Graph Learning for Scalable Subspace Clustering: From Single View to Multiview (2021, unknown): “Typically, these representative points are chosen based on K-means method (the cluster centers) or random sampling [62].”
Large-scale Multi-view Subspace Clustering in Linear Time (2019, methodology): “Anchor graph is an efﬁcient way to construct the large-scale graph matrix (Chen and Cai 2011; Liu, He, and Chang 2010; Wang et al. 2016a; Han, Xiong, and Nie 2017).”
TEM: Tree-enhanced Embedding Model for Explainable Recommendation (2018, background): “Note that optimizing other objective functions are also technically viable, such as the pointwise regression loss [20, 41, 42] and ranking loss [9, 33, 44].”
NAIS: Neural Attentive Item Similarity Model for Recommendation (2018, methodology): “Pointwise L2R methods either optimize a regression-based squared loss [1], [35] or classiﬁcation-based log loss [5], by either sampling negative feedback from missing data [36] or treating all missing data as negative feedback [6].”
Attentional Factorization Machines: Learning the Weight of Feature Interactions via Attention Networks (2017, background): “Another promising direction is to develop FM variants for semi-supervised and multi-view learning, for example by incorporating the widely used graph Laplacian [He et al. , 2017a; Wang et al. , 2016] and co-regularization designs [He et al. , 2014; Yang et al. , 2015].”
Stacked Autoencoders Driven by Semi-Supervised Learning for Building Extraction from near Infrared Remote Sensing Imagery (2021, methodology): “Overall, four novel semi-supervised schemes are adopted to estimate data labels for the vast amount of unlabeled data Anchor Graphs [40], SAFE Semi-Supervised Regression (SAFER) [41], Squared-loss Mutual Information Regularization [42], and an equal weighted importance of each of the above methods c”
Neural Factorization Machines for Sparse Predictive Analytics (2017, methodology): “While this work endows FM with non-linearities from predictive model perspective, another viable solution for incorporating nonlinearities is to extend the objective function with regularizers like the graph Laplacian [15, 34].”
Robust Anchor Embedding for Unsupervised Video Person re-IDentification in the Wild (2018, methodology): “A straightforward solution for label estimation is to design the graph Laplacian and conduct graph regularization as done in many anchor-graph based semi-supervised learning methods [25,31,37].”