ABSTRACT
In this paper, we first define information loss that occurs in the hypergraph expansion and then propose a novel framework, named MILEAGE, to evaluate hypergraph expansion methods by measuring their degree of information loss. MILEAGE employs the following four steps: (1) expanding a hypergraph; (2) performing the unsupervised representation learning on the expanded graph; (3) reconstructing a hypergraph based on vector representations obtained; and (4) measuring MILEAGE-score (i.e., mileage) by comparing the reconstructed and the original hypergraphs. To demonstrate the usefulness of MILEAGE, we conduct experiments via downstream tasks on three levels (i.e., node, hyperedge, and hypergraph): node classification, hyperedge prediction, and hypergraph classification on eight real-world hypergraph datasets. Through the extensive experiments, we observe that information loss through hypergraph expansion has a negative impact on downstream tasks and MILEAGE can effectively evaluate hypergraph expansion methods through the information loss and recommend a new method that resolves the problems of existing ones.
Supplemental Material
- A. Agarap. 2018. Deep Learning Using Rectified Linear Units (relu). arXiv preprint arXiv:1803.08375 (2018).Google Scholar
- S. Agarwal, K. Branson, and S. Belongie. 2006. Higher Order Learning with Graphs. In Proceedings of International Conference on Machine Learning (ICML). 17--24.Google Scholar
- J. Benson, R. Abebe, M. Schaub, A. Jadbabaie, and J. Kleinberg. 2018. Simplicial Closure and Higher-Order Link Prediction. Proceedings of National Academy of Sciences USA, Vol. 115, 48 (2018), 11221--11230.Google ScholarCross Ref
- V. Blondel, J. Guillaume, R. Lambiotte, and E. Lefebvre. 2008. Fast Unfolding of Communities in Large Networks. Journal of Statistical Mechanics: Theory and Experiment, Vol. 2008, 10 (2008), P10008.Google ScholarCross Ref
- L. Breiman. 2001. Random Forests. Machine learning, Vol. 45 (2001), 5--32.Google ScholarDigital Library
- S. Chen, E. Xie, C. Ge, R. Chen, D. Liang, and P. Luo. 2022. Cyclemlp: A Mlp-like Architecture for Dense Prediction. In Proceedings of International Conference on Learning Representations (ICLR).Google Scholar
- E. Chien, C. Pan, J. Peng, and O. Milenkovic. 2021a. You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks. In Proceedings of International Conference on Learning Representations (ICLR).Google Scholar
- E. Chien, C. Pan, J. Peng, and O. Milenkovic. 2021b. You are Allset: A Multiset Function Framework for Hypergraph Neural Networks. In Proceedings of International Conference on Learning Representations (ICLR).Google Scholar
- P. Chodrow, N. Veldt, and A. Benson. 2021. Generative Hypergraph Clustering: From Blockmodels to Modularity. Science Advances, Vol. 7, 28 (2021), 1--13.Google ScholarCross Ref
- I. Dhillon, Y. Guan, and B. Kulis. 2007. Weighted Graph Cuts without Eigenvectors a Multilevel Approach. IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 29, 11 (2007), 1944--1957.Google ScholarDigital Library
- M. Do, S. Yoon, B. Hooi, and K. Shin. 2020. Structural Patterns and Generative Models of Real-World Hypergraphs. In Proceedings of ACM International Conference on Knowledge Discovery and Data Mining (KDD). 176--186.Google Scholar
- Y. Feng, H. You, Z. Zhang, R. Ji, and Y. Gao. 2019. Hypergraph Neural Networks. In Proceedings of AAAI Conference on Artificial Intelligence (AAAI). 3558--3565.Google Scholar
- M. Gardner and S. Dorling. 1998. Artificial Neural Networks (the Multilayer Perceptron)-A Review of Applications in the Atmospheric Sciences. Atmospheric environment, Vol. 32, 14--15 (1998), 2627--2636.Google Scholar
- P. Goyal and E. Ferrara. 2018. Graph Embedding Techniques, Applications, and Performance: A Survey. Knowledge-Based Systems, Vol. 151 (2018), 78--94.Google ScholarCross Ref
- A. Grover and J. Leskovec. 2016. node2vec: Scalable Feature Learning for Networks. In Proceedings of ACM International Conference on Knowledge Discovery and Data Mining (KDD). 855--864.Google Scholar
- Yin H, A. Benson, J. Leskovec, and D. Gleich. 2017. Local Higher-Order Graph Clustering. In Proceedings of ACM International Conference on Knowledge Discovery and Data Mining (KDD). 555--564.Google Scholar
- J. Han, J. Pei, and M. Kamber. 2011. Data Mining: Concepts and Techniques. Morgan Kaufmann, Waltham, Massachusetts.Google Scholar
- Z. Han, X. Zheng, C. Chen, W. Cheng, and Y. Yao. 2023. Intra and Inter Domain HyperGraph Convolutional Network for Cross-Domain Recommendation. In Proceedings of ACM Web Conference (WWW). 449--459.Google Scholar
- X. He, K. Deng, X. Wang, Y. Li, Y. Zhang, and M. Wang. 2020. Lightgcn: Simplifying and Powering Graph Convolution Network for Recommendation. In Proceedings of International ACM Conference on Research and Development in Information Retrieval (SIGIR). 639--648.Google Scholar
- R. Henderson, D. Clevert, and F. Montanari. 2021. Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity. In Proceedings of International Conference on Machine Learning (ICML). 4203--4213.Google Scholar
- H. Hwang, S. Lee, C. Park, and K. Shin. 2022. AHP: Learning to Negative Sample for Hyperedge Prediction. In Proceedings of International ACM Conference on Research and Development in Information Retrieval (SIGIR). 2237--2242.Google Scholar
- M. Jang, Y. Ko, H. Gwon, I. Jo, Y. Park, and S. Kim. 2023. SAGE: A Storage-Based Approach for Scalable and Efficient Sparse Generalized Matrix-Matrix Multiplication. In Proceedings of ACM International Conference on Information and Knowledge Management (CIKM). 923--933.Google Scholar
- Y. Kang, W. Lee, Y. Lee, K. Han, and S. Kim. 2021. Adversarial Learning of Balanced Triangles for Accurate Community Detection on Signed Networks. In Proceedings of IEEE International Conference on Data Mining (ICDM). 1150--1155.Google Scholar
- T. Kim, J. Heo, H. Kim, K. Shin, and S. Kim. 2024. VITA:'Carefully Chosen and Weighted Less' Is Better in Medication Recommendation. In Proceedings of AAAI Conference on Artificial Intelligence (AAAI).Google Scholar
- T. Kipf and M. Welling. 2017. Semi-Supervised Classification with Graph Convolutional Networks. In Proceedings of International Conference on Learning Representations (ICLR).Google Scholar
- D. Kleinbaum, L. Dietz, M. Gail, M. Klein, and M. Klein. 2002. Logistic Regression. Springer.Google Scholar
- Y. Kook, J. Ko, and K. Shin. 2020. Evolution of Real-World Hypergraphs: Patterns and Models without Oracles. In Proceedings of ACM International Conference on Information and Knowledge Management (CIKM). 272--281.Google Scholar
- A. Kumar, S. Singh, K. Singh, and B. Biswas. 2020. Link Prediction Techniques, Applications, and Performance: A survey. Physica A: Statistical Mechanics and its Applications, Vol. 553 (2020), 124289.Google Scholar
- D. Lee and K. Shin. 2023. I'm me, we're us, and i'm us: Tri-directional contrastive learning on hypergraphs. In Proceedings of AAAI Conference on Artificial Intelligence (AAAI). 8456--8464.Google Scholar
- Y. Lee, N. Seo, K. Han, and S. Kim. 2020. ASiNE: Adversarial Signed Network Embedding. In Proceedings of International ACM Conference on Research and Development in Information Retrieval (SIGIR). 609--618.Google Scholar
- J. Leskovec and C. Faloutsos. 2006. Sampling From Large Graphs. In Proceedings of ACM International Conference on Knowledge Discovery and Data Mining (KDD). 631--636.Google Scholar
- M. Newman. 2014. Coauthorship Networks and Patterns of Scientific Collaboration. Proceedings of National Academy of Sciences USA, Vol. 101 (2014), 5200--5205.Google ScholarCross Ref
- W. Noble. 2006. What is a Support Vector Machine? Nature biotechnology, Vol. 24, 12 (2006), 1565--1567.Google Scholar
- P. Patil, G. Sharma, and M. Murty. 2020. Negative Sampling for Hyperlink Prediction in Networks. In Proceedings of Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD). 607--619.Google Scholar
- B. Perozzi, R. Al-Rfou, and S. Skiena. 2014. Deepwalk: Online Learning of Social Representations. In Proceedings of ACM International Conference on Knowledge Discovery and Data Mining (KDD). 701--710.Google Scholar
- R. Rossi and N. Ahmed. 2015. The Network Data Repository with Interactive Graph Analytics and Visualization. In Proceedings of AAAI Conference on Artificial Intelligence (AAAI). 4292--4293.Google Scholar
- X. Su, S. Xue, F. Liu, J. Wu, J. Yang, C. Zhou, W. Hu, C. Paris, S. Nepal, D. Jin, Q. Sheng, and P. Yu. 2022. A Comprehensive Survey on Community Detection with Deep Learning. IEEE Transactions on Neural Networks and Learning Systems (2022).Google Scholar
- L. Sun, S. Ji, and J. Ye. 2008. Spectral Learning for Multi-Label Classification. In Proceedings of ACM International Conference on Knowledge Discovery and Data Mining (KDD). 668--676.Google Scholar
- S. Thakoor, C. Tallec, M. Azar, M. Azabou, E. Dyer, R. Munos, P. Velivc ković, and M. Valko. 2021. Large-scale Representation Learning on Graphs via Bootstrapping. (2021).Google Scholar
- K. Tu, P. Cui, X. Wang, F. Wang, and W. Zhu. 2018. Structural Deep Embedding for Hyper-Networks. In Proceedings of AAAI Conference on Artificial Intelligence (AAAI). 426--433.Google Scholar
- Nate Veldt. 2023. Cut-Matching Games for Generalized Hypergraph Ratio Cuts. In Proceedings of ACM Web Conference (WWW). 694--704.Google ScholarDigital Library
- N. Veldt, A. Benson, and J. Kleinberg. 2020. Minimizing Localized Ratio Cut Objectives in Hypergraphs. In Proceedings of ACM International Conference on Knowledge Discovery and Data Mining (KDD). 1708--1718.Google Scholar
- P. Velivc ković, G. Cucurull, A. Casanova, A. Romero, P. Lio, and Y. Bengio. 2017. Graph Attention Networks. arXiv preprint arXiv:1710.10903 (2017).Google Scholar
- P. Velivc ković, W. Fedus, W. Hamilton, P. Liò, Y. Bengio, and R. Hjelm. 2018. Deep Graph Infomax. In Proceedings of International Conference on Learning Representations (ICLR).Google Scholar
- S. Wang, L. Hu, Y. Wang, X. He, Q. Sheng, M. Orgun, L. Cao, F. Ricci, and P. Yu. 2021. Graph Learning Based Recommender Systems: A Review. arXiv preprint arXiv:2105.06339 (2021).Google Scholar
- J. Wu, S. Li, J. Li, Y. Pan, and K. Xu. 2022. A Simple yet Effective Method for Graph Classification. In Proceedings of International Joint Conference on Artificial Intelligence (IJCAI). 3580--3586.Google Scholar
- C. Yang, R. Wang, S. Yao, and T. Abdelzaher. 2022. Semi-Supervised Hypergraph Node Classification on Hypergraph Line Expansion. In Proceedings of ACM International Conference on Information and Knowledge Management (CIKM). 2352--2361.Google Scholar
- J. Yang and J. Leskovec. 2012. Defining and Evaluating Network Communities Based on Ground-Truth. In Proceedings of IEEE International Conference on Data Mining (ICDM). 745--754.Google Scholar
- H. Yoo, Y. Lee, K. Shin, and S. Kim. 2022. Directed Network Embedding with Virtual Negative Edges. In Proceedings of ACM International Conference on Web Search and Data Mining (WSDM). 1291--1299.Google Scholar
- H. Yoo, Y. Lee, K. Shin, and S. Kim. 2023. Disentangling Degree-related Biases and Interest for Out-of-Distribution Generalized Directed Network Embedding. In Proceedings of ACM Web Conference (WWW). 231--239.Google Scholar
- J. Yu, H. Yin, J. Li, Q. Wang, N. Hung, and X. Zhang. 2021. Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendation. In Proceedings of ACM Web Conference (WWW). 413--424.Google Scholar
- R. Zhang, Y. Zou, and J. Ma. 2020. Hyper-SAGNN: A Self-Attention Based Graph Neural Network for Hypergraphs. In Proceedings of International Conference on Learning Representations (ICLR).Google Scholar
- C. Zheng, X. Fan, C. Wang, and J. Qi. 2020. Defining and Evaluating Network Communities Based on Ground-Truth. In Proceedings of AAAI Conference on Artificial Intelligence (AAAI). 1234--1241.Google Scholar
- D. Zhou, J. Huang, and B. Scholköpf. 2006. Learning with Hypergraphs: Clustering, Classification, and Embedding. In Proceedings of Conference on Neural Information Processing Systems (NIPS). 1633--1640.Google Scholar
Index Terms
- Low Mileage, High Fidelity: Evaluating Hypergraph Expansion Methods by Quantifying the Information Loss
Recommendations
Semi-supervised Hypergraph Node Classification on Hypergraph Line Expansion
CIKM '22: Proceedings of the 31st ACM International Conference on Information & Knowledge ManagementPrevious hypergraph expansions are solely carried out on either vertex level or hyperedge level, thereby missing the symmetric nature of data co-occurrence, and resulting in information loss. To address the problem, this paper treats vertices and ...
The Ramsey number for hypergraph cycles I
Let Cn denote the 3-uniform hypergraph loose cycle, that is the hypergraph with vertices v1.....,vn and edges v1v2v3, v3v4v5, v5v6v7,.....,vn-1vnv1. We prove that every red-blue colouring of the edges of the complete 3-uniform hypergraph with N vertices ...
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 ...
Comments