Parameter-Free Auto-Weighted Multiple Graph Learning: A Framework for Multiview Clustering and Semi-Supervised Classification

By Feiping Nie, Jing Li, Xuelong Li. International Joint Conference on Artificial Intelligence, 2016

644 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/ca690b2e7ae76338afd4a825b41175c6eaf6eb18

How researchers see this paper

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

1. Ling Shao
2. Li Liu
3. Zheng Zhang
4. Yi Yang
5. Fumin Shen
6. Heng Tao Shen
7. Wanli Ouyang
8. Yang Wang

Citations in the corpus

• Multi-view clustering: A survey (2018, unknown): “[63] evaluate the similarity by a predefined or fixed graph Laplacian in each view, separately, and neglect the underlying common structures across different views, Hou et al.”
• Multiview Consensus Graph Clustering (2019, background): “5) AMGL: Auto-weighted multiple graph learning (AMGL) [56] learns the view weight adaptively and sums up different Laplacian matrices from different views to calculate”
• GMC: Graph-Based Multi-View Clustering (2020, methodology): “Most relatedworks to ours are those in [5], [6], [7], [8], [9], [10], [11], [12], which are existing multi-view graph-based clusteringmethods.”
• Multiview Spectral Clustering via Structured Low-Rank Matrix Factorization (2017, methodology): “Besides, the latest non-parametric graph construction model [ Nie et al. , 2016b ] will also be incorporated for multi-view spectral clustering.”
• Dual Contrastive Prediction for Incomplete Multi-View Representation Learning (2022, unknown): “(5) AMGL (Auto-Weight Multiple Graph Learning) [74] is a supervised multi-view classification method which learns an optimal weight for each graph.”
• Binary Multi-View Clustering (2019, methodology): “, k-means) to group data; the second category is the multi-view spectral clustering methods [11], [19], [20], [21], [22], which construct multiple graphs to characterize the geometrical structure and employ an existing clustering method for data partition; the third category is based on matrix facto”
• Multi-View Clustering and Semi-Supervised Classification with Adaptive Neighbours (2017, methodology): “One important factor to the success of graph-based methods is the preserving local manifold structure, high-dimensional data is considered to contain low-dimensional manifold structure (Nie, Li, and Li 2016), so the obtained similarity matrix is crucial to the ultimate performance.”
• Scalable Multi-view Subspace Clustering with Unified Anchors (2021, methodology): “Parameter-free Auto-weighted Multiple Graph Learning (AMGL) [23] automatically learns the optimal weights for each graph and obtains globally optimal results.”
• Large-scale Multi-view Subspace Clustering in Linear Time (2019, unknown): “Parameter-Free Auto-Weighted Multiple Graph Learning (AMGL) : one of the state-of-the-art multi-view spectral clustering method proposed in (Nie et al. 2016).”
• Deep multi-view learning methods: A review (2021, methodology): “The traditional MF-based MVL approaches can be partitioned into two types: multiple kernel/graph [114, 115, 116, 117] and subspace learning methods [118, 119].”