ABSTRACT
Graph-based learning methods explicitly consider the relations between two entities (i.e., vertices) for learning the prediction function. They have been widely used in semi-supervised learning, manifold ranking, and clustering, among other tasks. Enhancing the expressiveness of simple graphs, hypergraphs formulate an edge as a link to multiple vertices, so as to model the higher-order relations among entities. For example, hyperedges in a hypergraph can be used to encode the similarity among vertices.
To the best of our knowledge, all existing hypergraph structures represent the hyperedge as an unordered set of vertices, without considering the possible ordering relationship among vertices. In real-world data, ordering relations commonly exist, such as in graded categorical features (e.g., users» ratings on movies) and numerical features (e.g., monthly income of customers). When constructing a hypergraph, ignoring such ordering relations among entities will lead to severe information loss, resulting in suboptimal performance of the subsequent learning algorithms.
In this work, we address the inherent limitation of existing hypergraphs by proposing a new data structure named Partial-Order Hypergraph, which specifically injects the partially ordering relations among vertices into a hyperedge. We develop regularization-based learning theories for partial-order hypergraphs, generalizing conventional hypergraph learning by incorporating logical rules that encode the partial-order relations. We apply our proposed method to two applications: university ranking from Web data and popularity prediction of online content. Extensive experiments demonstrate the superiority of our proposed partial-order hypergraphs, which consistently improve over conventional hypergraph methods.
- Charu C Aggarwal and Chandan K Reddy. 2013. Data clustering: algorithms and applications. CRC press. Google ScholarDigital Library
- Stephen H. Bach, Matthias Broecheler, Bert Huang, and Lise Getoor. 2017. Hinge-Loss Markov Random Fields and Probabilistic Soft Logic. Journal of Machine Learning Research (2017). Google ScholarDigital Library
- Abdelghani Bellaachia and Mohammed Al-Dhelaan. 2014. Multi-document hyperedge-based ranking for text summarization CIKM. 1919--1922. Google ScholarDigital Library
- Chen Chen, Cewu Lu, Qixing Huang, Qiang Yang, Dimitrios Gunopulos, and Leonidas Guibas. 2016 a. City-Scale Map Creation and Updating Using GPS Collections SIGKDD. 1465--1474. Google ScholarDigital Library
- Jingyuan Chen, Xuemeng Song, Liqiang Nie, Xiang Wang, Hanwang Zhang, and Tat-Seng Chua. 2016 b. Micro tells macro: predicting the popularity of micro-videos via a transductive model MM. 898--907. Google ScholarDigital Library
- Zhiyong Cheng and Jialie Shen. 2016. On effective location-aware music recommendation. Transactions on Information System Vol. 34, 2 (2016), 13. Google ScholarDigital Library
- Paolo Cremonesi, Yehuda Koren, and Roberto Turrin. 2010. Performance of Recommender Algorithms on Top-n Recommendation Tasks RecSys. 39--46. Google ScholarDigital Library
- Inderjit S Dhillon, Yuqiang Guan, and Brian Kulis. 2004. Kernel k-means: spectral clustering and normalized cuts SIGKDD. 551--556. Google ScholarDigital Library
- Fuli Feng, Liqiang Nie, Xiang Wang, Richang Hong, and Tat-Seng Chua. 2017 a. Computational social indicators: a case study of chinese university ranking SIGIR. 455--464. Google ScholarDigital Library
- Xiaodong Feng, Sen Wu, and Wenjun Zhou. 2017 b. Multi-Hypergraph Consistent Sparse Coding. Transactions on Intelligent Systems and Technology, Vol. 8, 6 (2017), 75. Google ScholarDigital Library
- David F Gleich and Michael W Mahoney. 2015. Using local spectral methods to robustify graph-based learning algorithms SIGKDD. 359--368. Google ScholarDigital Library
- Ian Goodfellow, Yoshua Bengio, and Aaron Courville. 2016. Deep learning. MIT press. Google ScholarDigital Library
- Richard HR Hahnloser, Rahul Sarpeshkar, Misha A Mahowald, Rodney J Douglas, and H Sebastian Seung. 2000. Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit. Nature, Vol. 405, 6789 (2000), 947.Google Scholar
- Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770--778.Google Scholar
- Xiangnan He and Tat-Seng Chua. 2017. Neural Factorization Machines for Sparse Predictive Analytics SIGIR. 355--364. Google ScholarDigital Library
- Xiangnan He, Ming Gao, Min-Yen Kan, Yiqun Liu, and Kazunari Sugiyama. 2014. Predicting the Popularity of Web 2.0 Items Based on User Comments SIGIR. 233--242. Google ScholarDigital Library
- Xiangnan He, Ming Gao, Min-Yen Kan, and Dingxian Wang. 2017. Birank: Towards ranking on bipartite graphs. Transactions on Knowledge and Data Engineering, Vol. 29, 1 (2017), 57--71. Google ScholarDigital Library
- Manel Hmimida and Rushed Kanawati. 2016. A Graph-Coarsening Approach for Tag Recommendation WWW. 43--44. Google ScholarDigital Library
- Sheng Huang, Mohamed Elhoseiny, Ahmed Elgammal, and Dan Yang. 2015. Learning hypergraph-regularized attribute predictors CVPR. 409--417.Google Scholar
- Jyun-Yu Jiang, Pu-Jen Cheng, and Wei Wang. 2017. Open Source Repository Recommendation in Social Coding SIGIR. 1173--1176. Google ScholarDigital Library
- Thomas N Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. ICLR (2017).Google Scholar
- Lei Li and Tao Li. 2013. News recommendation via hypergraph learning: encapsulation of user behavior and news content WSDM. 305--314. Google ScholarDigital Library
- David C Liu, Stephanie Rogers, Raymond Shiau, Dmitry Kislyuk, Kevin C Ma, Zhigang Zhong, Jenny Liu, and Yushi Jing. 2017 a. Related pins at pinterest: The evolution of a real-world recommender system WWW. 583--592. Google ScholarDigital Library
- Qingshan Liu, Yubao Sun, Cantian Wang, Tongliang Liu, and Dacheng Tao. 2017 b. Elastic net hypergraph learning for image clustering and semi-supervised classification. Transactions on Image Processing Vol. 26, 1 (2017), 452--463. Google ScholarDigital Library
- Tie-Yan Liu. 2011. Learning to rank for information retrieval. Springer Science & Business Media.Google ScholarDigital Library
- Tao Mei, Yong Rui, Shipeng Li, and Qi Tian. 2014. Multimedia search reranking: A literature survey. Comput. Surveys Vol. 46, 3 (2014), 38. Google ScholarDigital Library
- Michael Mitzenmacher, Jakub Pachocki, Richard Peng, Charalampos Tsourakakis, and Shen Chen Xu. 2015. Scalable large near-clique detection in large-scale networks via sampling SIGKDD. 815--824. Google ScholarDigital Library
- RB Nelsen. 2001. Kendall tau metric. Encyclopaedia of Mathematics Vol. 3 (2001), 226--227.Google Scholar
- Liqiang Nie, Meng Wang, Zheng-Jun Zha, and Tat-Seng Chua. 2012 a. Oracle in image search: a content-based approach to performance prediction. Transactions on Information System Vol. 30, 2 (2012), 13. Google ScholarDigital Library
- Liqiang Nie, Shuicheng Yan, Meng Wang, Richang Hong, and Tat-Seng Chua. 2012 b. Harvesting visual concepts for image search with complex queries MM. 59--68. Google ScholarDigital Library
- Adi Omari, David Carmel, Oleg Rokhlenko, and Idan Szpektor. 2016. Novelty Based Ranking of Human Answers for Community Questions SIGIR. 215--224. Google ScholarDigital Library
- Xiang Ren, Ahmed El-Kishky, Chi Wang, Fangbo Tao, Clare R. Voss, and Jiawei Han. 2015. ClusType: Effective Entity Recognition and Typing by Relation Phrase-Based Clustering SIGKDD. 995--1004. Google ScholarDigital Library
- Marian-Andrei Rizoiu, Lexing Xie, Scott Sanner, Manuel Cebrian, Honglin Yu, and Pascal Van Hentenryck. 2017. Expecting to Be HIP: Hawkes Intensity Processes for Social Media Popularity WWW. 735--744. Google ScholarDigital Library
- Charles Spearman. 1987. The proof and measurement of association between two things. The American journal of psychology Vol. 100 (1987), 441--471.Google Scholar
- Kenneth Tran, Saghar Hosseini, Lin Xiao, Thomas Finley, and Mikhail Bilenko. 2015. Scaling up stochastic dual coordinate ascent. In SIGKDD. 1185--1194. Google ScholarDigital Library
- Charalampos E Tsourakakis, Jakub Pachocki, and Michael Mitzenmacher. 2017. Scalable motif-aware graph clustering. In WWW. 1451--1460. Google ScholarDigital Library
- Meng Wang, Weijie Fu, Shijie Hao, Dacheng Tao, and Xindong Wu. 2016 a. Scalable semi-supervised learning by efficient anchor graph regularization. Transactions on Knowledge and Data Engineering, Vol. 28, 7 (2016), 1864--1877.Google ScholarCross Ref
- Meng Wang, Xueliang Liu, and Xindong Wu. 2015. Visual Classification by $ell _1$ -Hypergraph Modeling. TKDE, Vol. 27, 9 (2015), 2564--2574.Google ScholarDigital Library
- Xiang Wang, Xiangnan He, Liqiang Nie, and Tat-Seng Chua. 2017. Item silk road: Recommending items from information domains to social users SIGIR. 185--194. Google ScholarDigital Library
- Xiaoqian Wang, Feiping Nie, and Heng Huang. 2016 b. Structured Doubly Stochastic Matrix for Graph Based Clustering: Structured Doubly Stochastic Matrix SIGKDD. 1245--1254. Google ScholarDigital Library
- Cort J Willmott and Kenji Matsuura. 2005. Advantages of the mean absolute error (MAE) over the root mean square error (RMSE) in assessing average model performance. Climate research, Vol. 30, 1 (2005), 79--82.Google Scholar
- Yuichi Yoshida. 2014. Almost linear-time algorithms for adaptive betweenness centrality using hypergraph sketches. In SIGKDD. 1416--1425. Google ScholarDigital Library
- Hsiang-Fu Yu, Cho-Jui Hsieh, Hyokun Yun, SVN Vishwanathan, and Inderjit S Dhillon. 2015. A scalable asynchronous distributed algorithm for topic modeling WWW. 1340--1350. Google ScholarDigital Library
- Rose Yu, Huida Qiu, Zhen Wen, ChingYung Lin, and Yan Liu. 2016. A survey on social media anomaly detection. SIGKDD, Vol. 18, 1 (2016), 1--14. Google ScholarDigital Library
- Dongxiang Zhang, Long Guo, Xiangnan He, Jie Shao, Sai Wu, and Heng Tao Shen. 2018. A Graph-Theoretic Fusion Framework for Unsupervised Entity Resolution ICDE.Google Scholar
- Hanwang Zhang, Fumin Shen, Wei Liu, Xiangnan He, Huanbo Luan, and Tat-Seng Chua. 2016. Discrete collaborative filtering. In SIGIR. 325--334. Google ScholarDigital Library
- Denny Zhou, Olivier Bousquet, Thomas N Lal, Jason Weston, and Bernhard Schölkopf. 2004 a. Learning with local and global consistency. In NIPS. 321--328. Google ScholarDigital Library
- Denny Zhou, Jiayuan Huang, and Bernhard Schölkopf. 2007. Learning with hypergraphs: Clustering, classification, and embedding NIPS. 1601--1608. Google ScholarDigital Library
- Denny Zhou, Jason Weston, Arthur Gretton, Olivier Bousquet, and Bernhard Schölkopf. 2004 b. Ranking on data manifolds. In NIPS. 169--176. Google ScholarDigital Library
Index Terms
- Learning on Partial-Order Hypergraphs
Recommendations
Covering Non-uniform Hypergraphs
A subset of the vertices in a hypergraph is a cover if it intersects every edge. Let (H) denote the cardinality of a minimum cover in the hypergraph H, and let us denote by g(n) the maximum of (H) taken over all hypergraphs H with n vertices and with no ...
Odd cycles and Θ-cycles in hypergraphs
A @Q-cycle of a hypergraph is a cycle including an edge that contains at least three base points of the cycle. We show that if a hypergraph H=(V,E) has no @Q-cycle, and |e|>=3, for every edge e@__ __E, then @__ __"e"@__ __"E(|e|-1)=<2|V|-2 with equality ...
Maximally edge-connected hypergraphs
The edge-connectivity of a connected graph or hypergraph is the minimum number of edges whose removal renders the graph or hypergraph, respectively, disconnected. The edge-connectivity of a (hyper) graph cannot exceed its minimum degree. For graphs, ...
Comments