### Abstract

Attributed graphs are increasingly more common in many application domains such as chemistry, biology and text processing. A central issue in graph mining is how to collect informative subgraph patterns for a given learning task. We propose an iterative mining method based on partial least squares regression (PLS). To apply PLS to graph data, a sparse version of PLS is developed first and then it is combined with a weighted pattern mining algorithm. The mining algorithm is iteratively called with different weight vectors, creating one latent component per one mining call. Our method, graph PLS, is efficient and easy to implement, because the weight vector is updated with elementary matrix calculations. In experiments, our graph PLS algorithm showed competitive prediction accuracies in many chemical datasets and its efficiency was significantly superior to graph boosting (gBoost) and the naive method based on frequent graph mining.

Original language | English |
---|---|

Title of host publication | KDD 2008 - Proceedings of the 14th ACMKDD International Conference on Knowledge Discovery and Data Mining |

Pages | 578-586 |

Number of pages | 9 |

DOIs | |

Publication status | Published - Dec 1 2008 |

Externally published | Yes |

Event | 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2008 - Las Vegas, NV, United States Duration: Aug 24 2008 → Aug 27 2008 |

### Publication series

Name | Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining |
---|

### Other

Other | 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2008 |
---|---|

Country | United States |

City | Las Vegas, NV |

Period | 8/24/08 → 8/27/08 |

### Fingerprint

### All Science Journal Classification (ASJC) codes

- Software
- Information Systems

### Cite this

*KDD 2008 - Proceedings of the 14th ACMKDD International Conference on Knowledge Discovery and Data Mining*(pp. 578-586). (Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining). https://doi.org/10.1145/1401890.1401961

**Partial least squares regression for graph mining.** / Saigo, Hiroto; Krämer, Nicole; Tsuda, Koji.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

*KDD 2008 - Proceedings of the 14th ACMKDD International Conference on Knowledge Discovery and Data Mining.*Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 578-586, 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD 2008, Las Vegas, NV, United States, 8/24/08. https://doi.org/10.1145/1401890.1401961

}

TY - GEN

T1 - Partial least squares regression for graph mining

AU - Saigo, Hiroto

AU - Krämer, Nicole

AU - Tsuda, Koji

PY - 2008/12/1

Y1 - 2008/12/1

N2 - Attributed graphs are increasingly more common in many application domains such as chemistry, biology and text processing. A central issue in graph mining is how to collect informative subgraph patterns for a given learning task. We propose an iterative mining method based on partial least squares regression (PLS). To apply PLS to graph data, a sparse version of PLS is developed first and then it is combined with a weighted pattern mining algorithm. The mining algorithm is iteratively called with different weight vectors, creating one latent component per one mining call. Our method, graph PLS, is efficient and easy to implement, because the weight vector is updated with elementary matrix calculations. In experiments, our graph PLS algorithm showed competitive prediction accuracies in many chemical datasets and its efficiency was significantly superior to graph boosting (gBoost) and the naive method based on frequent graph mining.

AB - Attributed graphs are increasingly more common in many application domains such as chemistry, biology and text processing. A central issue in graph mining is how to collect informative subgraph patterns for a given learning task. We propose an iterative mining method based on partial least squares regression (PLS). To apply PLS to graph data, a sparse version of PLS is developed first and then it is combined with a weighted pattern mining algorithm. The mining algorithm is iteratively called with different weight vectors, creating one latent component per one mining call. Our method, graph PLS, is efficient and easy to implement, because the weight vector is updated with elementary matrix calculations. In experiments, our graph PLS algorithm showed competitive prediction accuracies in many chemical datasets and its efficiency was significantly superior to graph boosting (gBoost) and the naive method based on frequent graph mining.

UR - http://www.scopus.com/inward/record.url?scp=65449142148&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=65449142148&partnerID=8YFLogxK

U2 - 10.1145/1401890.1401961

DO - 10.1145/1401890.1401961

M3 - Conference contribution

AN - SCOPUS:65449142148

SN - 9781605581934

T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining

SP - 578

EP - 586

BT - KDD 2008 - Proceedings of the 14th ACMKDD International Conference on Knowledge Discovery and Data Mining

ER -