{"type":"ScholarlyArticle","title":"Understanding the Success of Graph-based Semi-Supervised Learning using Partially Labelled Stochastic Block Model","authors":[{"name":"Avirup Saha","slug":"avirup-saha","given":"Avirup","family":"Saha","affiliation":"Indian Institute of Technology , Kharagpur"},{"name":"Shreyas Sheshadri","slug":"shreyas-sheshadri","given":"Shreyas","family":"Sheshadri","affiliation":"Flipkart Internet Private Limited"},{"name":"Samik Datta","slug":"samik-datta","given":"Samik","family":"Datta","affiliation":"Flipkart Internet Private Limited"},{"name":"Niloy Ganguly","slug":"niloy-ganguly","given":"Niloy","family":"Ganguly","affiliation":"Indian Institute of Technology , Kharagpur"},{"name":"Disha Makhija","slug":"disha-makhija","given":"Disha","family":"Makhija","affiliation":"Flipkart Internet Private Limited"},{"name":"Priyank Patel","slug":"priyank-patel","given":"Priyank","family":"Patel","affiliation":"Flipkart Internet Private Limited"}],"abstract":"With the proliferation of learning scenarios with an abundance of instances, but limited amount of high-quality labels, semi-supervised learning algorithms came to prominence. Graph-based semi-supervised learning (G-SSL) algorithms, of which Label Propagation (LP) is a prominent example, are particularly well-suited for these problems. The premise of LP is the existence of homophily in the graph, but beyond that nothing is known about the efficacy of LP. In particular, there is no characterisation that connects the structural constraints, volume and quality of the labels to the accuracy of LP. In this work, we draw upon the notion of recovery from the literature on community detection, and provide guarantees on accuracy for partially-labelled graphs generated from the Partially-Labelled Stochastic Block Model (PLSBM). Extensive experiments performed on synthetic data verify the theoretical findings.","doi":"10.24963/ijcai.2020/187","url":"https://ijcai.org/proceedings/2020/187","pdf":"https://ijcai.org/proceedings/2020/0187.pdf","markdown":"https://ijcai.org/proceedings/2020/187.md","bibtex":"https://ijcai.org/proceedings/2020/bibtex/187","volume":{"slug":"2020","title":"Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2020","url":"https://ijcai.org/proceedings/2020/","year":2020,"location":"Yokohama","dates":"January 2021 (postponed from 11-17 July 2020)","editors":"Christian Bessiere","isbn":"978-0-9992411-6-5","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2020"},"section":"Data Mining","track":"Main track","number":187,"pages":{"first":1345,"last":1351},"keywords":["Data Mining: Mining Graphs, Semi Structured Data, Complex Data","Data Mining: Classification, Semi-Supervised Learning"],"videos":[{"label":"Video","url":"https://videos.ijcai20.org/24127/file_24127.m3u8","length_sec":307,"provider":"hls"}],"references":[{"position":1,"raw":"[Abbe and Sandon, 2015] Emmanuel Abbe and Colin San- don. Community detection in general stochastic block models: Fundamental limits and efficient algorithms for recovery. In 2015 IEEE 56th Annual Symposium on Foun- dations of Computer Science, pages 670-688. IEEE, 2015.","title":"Community detection in general stochastic block models: Fundamental limits and efficient algorithms for recovery","authors":"Abbe, Sandon","year":"2015","venue":"IEEE 56th Annual Symposium on Foundations of Computer Science","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Abbe et al., 2015] Emmanuel Abbe, Afonso S Bandeira, and Georgina Hall. Exact recovery in the stochastic block model. volume 62, pages 471-487. IEEE, 2015.","title":"Exact recovery in the stochastic block model","authors":"Emmanuel Abbe, Afonso S Bandeira, Georgina Hall","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Abbe, 2017] Emmanuel Abbe. Community detection and stochastic block models: recent developments. The Jour- nal of Machine Learning Research, 18(1):6446-6531, 2017.","title":"Community detection and stochastic block models: recent developments","authors":"Emmanuel Abbe","year":"2017","venue":"The Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bengio et al., 2006] Yoshua Bengio, Olivier Delalleau, and Nicolas Le Roux. 11 label propagation and quadratic cri- terion. researchgate.net, 2006.","title":"11 label propagation and quadratic criterion","authors":"Yoshua Bengio, Olivier Delalleau, Nicolas Le Roux","year":"2006","venue":null,"doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Chakrabarti et al., 2014] Deepayan Chakrabarti, Stanislav Funiak, Jonathan Chang, and Sofus A Macskassy. Joint inference of multiple label types in large networks. arXiv preprint arXiv:1401.7709, 2014.","title":"Joint inference of multiple label types in large networks","authors":"Chakrabarti","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Ke and Honorio, 2018] Chuyang Ke and Jean Honorio. Information-theoretic limits for community detection in network models. In Advances in Neural Information Pro- cessing Systems, pages 8324-8333, 2018.","title":"Information-theoretic limits for community detection in network models","authors":"Honorio Ke, Chuyang Ke, Jean Honorio","year":"2018","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Massoulié, 2014] Laurent Massoulié. Community detection thresholds and the weak ramanujan property. In Proceed- ings of the forty-sixth annual ACM symposium on Theory of computing, pages 694-703. ACM, 2014.","title":"Community detection thresholds and the weak ramanujan property","authors":"Laurent Massoulié","year":"2014","venue":"Proceedings of the forty-sixth annual ACM symposium on Theory of computing","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[McPherson et al., 2001] Miller McPherson, Lynn Smith- Lovin, and James M Cook. Birds of a feather: Homophily in social networks. Annual review of sociology, 27(1):415- 444, 2001.","title":"Birds of a feather: Homophily in social networks","authors":"Mcpherson","year":"2001","venue":"Annual review of sociology","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Saad and Nosratinia, 2018] Hussein Saad and Aria Nosra- tinia. Community detection with side information: Exact recovery under the stochastic block model. volume 12, pages 944-958. IEEE, 2018.","title":"Hussein Saad and Aria Nosratinia. Community detection with side information: Exact recovery under the stochastic block model","authors":"Nosratinia Saad","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Stretcu et al., 2019] Otilia Stretcu, Krishnamurthy Viswanathan, Dana Movshovitz-Attias, Emmanouil Platanios, Sujith Ravi, and Andrew Tomkins. Graph agreement models for semi-supervised learning. In H. Wallach, H. Larochelle, A. Beygelzimer, F. d'Alché- Buc, E. Fox, and R. Garnett, editors, Advances in Neural Information Processing Systems 32, pages 8710-8720.","title":"Graph agreement models for semi-supervised learning","authors":"Otilia Stretcu, Krishnamurthy Viswanathan, Dana Movshovitz-Attias, Emmanouil Platanios, Sujith Ravi, Andrew Tomkins","year":null,"venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"Curran Associates, Inc., 2019.","title":null,"authors":"Curran Associates, Inc","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Talukdar and Crammer, 2009] Partha Pratim Talukdar and Koby Crammer. New regularized algorithms for transduc- tive learning. In Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pages 442-457. Springer, 2009.","title":"New regularized algorithms for transductive learning","authors":"Partha Pratim, Talukdar, Koby Crammer","year":"2009","venue":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Yamaguchi and Hayashi, 2017] Yuto Yamaguchi and Kohei Hayashi. When does label propagation fail? a view from a network generative model. In IJCAI, pages 3224-3230, 2017.","title":"When does label propagation fail? a view from a network generative model","authors":"Hayashi ; ] Yuto Yamaguchi, Kohei Yamaguchi, Hayashi","year":"2017","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/450"},{"position":14,"raw":"[Yun and Proutiere, 2014] Se-Young Yun and Alexandre Proutiere. Accurate community detection in the stochas- tic block model via spectral algorithms. arXiv preprint arXiv:1412.7335, 2014.","title":"Se-Young Yun and Alexandre Proutiere. Accurate community detection in the stochastic block model via spectral algorithms","authors":"Proutiere Yun","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Zhu et al., 2003] Xiaojin Zhu, Zoubin Ghahramani, and John D Lafferty. Semi-supervised learning using gaussian fields and harmonic functions. In Proceedings of the 20th International conference on Machine learning (ICML-03), pages 912-919, 2003.","title":"Semi-supervised learning using gaussian fields and harmonic functions","authors":"Xiaojin Zhu, Zoubin Ghahramani, John D Lafferty","year":"2003","venue":"Proceedings of the 20th International conference on Machine learning (ICML-03)","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Zhu, 2005] Xiaojin Zhu. Semi-supervised learning with graphs. PhD thesis, Carnegie Mellon University, language technologies institute, school of, 2005.","title":"Semi-supervised learning with graphs","authors":"Xiaojin Zhu","year":"2005","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}