2000 character limit reached
Upper Bounding Barlow Twins: A Novel Filter for Multi-Relational Clustering (2312.14066v1)
Published 21 Dec 2023 in cs.LG
Abstract: Multi-relational clustering is a challenging task due to the fact that diverse semantic information conveyed in multi-layer graphs is difficult to extract and fuse. Recent methods integrate topology structure and node attribute information through graph filtering. However, they often use a low-pass filter without fully considering the correlation among multiple graphs. To overcome this drawback, we propose to learn a graph filter motivated by the theoretical analysis of Barlow Twins. We find that input with a negative semi-definite inner product provides a lower bound for Barlow Twins loss, which prevents it from reaching a better solution. We thus learn a filter that yields an upper bound for Barlow Twins. Afterward, we design a simple clustering architecture and demonstrate its state-of-the-art performance on four benchmark datasets.
- Graph barlow twins: A self-supervised representation learning framework for graphs. Knowledge-Based Systems, 256: 109631.
- Kernel density estimation via diffusion. Annals of Statistics, 38(5): 2916–2957.
- A simple framework for contrastive learning of visual representations. In International conference on machine learning, 1597–1607. PMLR.
- Exploring simple siamese representation learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 15750–15758.
- Multi-view attribute graph convolution networks for clustering. In Proceedings of the twenty-ninth international conference on international joint conferences on artificial intelligence, 2973–2979.
- One2multi graph autoencoder for multi-view graph clustering. In proceedings of the web conference 2020, 3070–3076.
- Structure-preserving graph representation learning. In 2022 IEEE International Conference on Data Mining (ICDM), 927–932. IEEE.
- Bootstrap your own latent-a new approach to self-supervised learning. Advances in neural information processing systems, 33: 21271–21284.
- Momentum contrast for unsupervised visual representation learning. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, 9729–9738.
- Ups and downs: Modeling the visual evolution of fashion trends with one-class collaborative filtering. In proceedings of the 25th international conference on world wide web, 507–517.
- Higham, N. J. 2002. Accuracy and stability of numerical algorithms. SIAM.
- Graphmae: Self-supervised masked graph autoencoders. In Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 594–604.
- Hdmi: High-order deep multiplex infomax. In Proceedings of the Web Conference 2021, 2414–2424.
- Adam: A Method for Stochastic Optimization. In Proceedings of the International Conference on Learning Representations (ICLR) 2015.
- On information and sufficiency. The annals of mathematical statistics, 22(1): 79–86.
- Graph Filter-based Multi-view Attributed Graph Clustering. In IJCAI, 2723–2729.
- Multi-View Attributed Graph Clustering. IEEE Transactions on Knowledge & Data Engineering, 35(02): 1872–1880.
- Multilayer Graph Contrastive Clustering Network. Inf. Sci., 613(C): 256–267.
- Deep graph clustering via dual correlation reduction. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 36, 7603–7611.
- Understanding latent correlation-based multiview learning and self-supervision: An identifiability perspective. In International Conference on Learning Representations.
- Multiplex Graph Representation Learning Via Dual Correlation Reduction. IEEE Transactions on Knowledge and Data Engineering.
- Self-weighted Multiview Clustering with Multiple Graphs. In IJCAI, 2564–2570.
- Multi-view contrastive graph clustering. Advances in neural information processing systems, 34: 2148–2159.
- Beyond Homophily: Reconstructing Structure for Graph-agnostic Clustering. In Proceedings of the 40th International Conference on Machine Learning, 26868–26877.
- High-order multi-view clustering for generic data. Information Fusion, 100: 101947.
- An attention-based collaboration framework for multi-view network representation learning. In Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, 1767–1776.
- Deep fusion clustering network. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 35, 9978–9987.
- Heterogeneous Graph Attention Network. In The World Wide Web Conference, WWW ’19, 2022–2032.
- Self-supervised heterogeneous graph neural network with co-contrastive learning. In Proceedings of the 27th ACM SIGKDD conference on knowledge discovery & data mining, 1726–1736.
- Consistent multiple graph embedding for multi-view clustering. IEEE Transactions on Multimedia.
- Multi-view graph embedding clustering network: Joint self-supervision and block diagonal representation. Neural Networks, 145: 1–9.
- Barlow twins: Self-supervised learning via redundancy reduction. In International Conference on Machine Learning, 12310–12320. PMLR.
- Align representations with base: A new approach to self-supervised learning. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 16600–16609.
- Zero-cl: Instance and feature decorrelation for negative-free symmetric contrastive learning. In International Conference on Learning Representations.
- Attributed graph clustering via adaptive graph convolution. In 28th International Joint Conference on Artificial Intelligence, IJCAI 2019.
Sponsor
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.