Transfer Knowledge between Cities

ABSTRACT

The rapid urbanization has motivated extensive research on urban computing. It is critical for urban computing tasks to unlock the power of the diversity of data modalities generated by different sources in urban spaces, such as vehicles and humans. However, we are more likely to encounter the label scarcity problem and the data insufficiency problem when solving an urban computing task in a city where services and infrastructures are not ready or just built. In this paper, we propose a FLexible multimOdal tRAnsfer Learning (FLORAL) method to transfer knowledge from a city where there exist sufficient multimodal data and labels, to this kind of cities to fully alleviate the two problems. FLORAL learns semantically related dictionaries for multiple modalities from a source domain, and simultaneously transfers the dictionaries and labelled instances from the source into a target domain. We evaluate the proposed method with a case study of air quality prediction.

References

1. J. L. Bentley. Multidimensional binary search trees used for associative searching. Communications of the ACM, 18(9):509--517, 1975.
2. J. Blitzer, S. Kakade, and D. P. Foster. Domain adaptation with coupled subspaces. In AISTATS, pages 173--181, 2011.
3. T. M. Cover and J. A. Thomas. Elements of information theory. 2012.
4. W. Dai, Q. Yang, G.-R. Xue, and Y. Yu. Boosting for transfer learning. In ICML, pages 193--200, 2007.
5. Z. Fang and Z. M. Zhang. Discriminative feature selection for multi-view cross-domain learning. In CIKM, pages 1321--1330, 2013.
6. D. R. Hardoon, S. Szedmak, and J. Shawe-Taylor. Canonical correlation analysis: An overview with application to learning methods. Neural computation, 16(12):2639--2664, 2004.
7. J. He and R. Lawrence. A graph-based framework for multi-task multi-view learning. In ICML, pages 25--32, 2011.
8. Z. Jiang, G. Zhang, and L. S. Davis. Submodular dictionary learning for sparse coding. In CVPR, pages 3418--3425, 2012.
9. X. Jin, F. Zhuang, H. Xiong, C. Du, P. Luo, and Q. He. Multi-task multi-view learning for heterogeneous tasks. In CIKM, pages 441--450, 2014.
10. R. Kiros, R. Salakhutdinov, and R. Zemel. Multimodal neural language models. In ICML, pages 595--603, 2014.
11. M.-Y. Liu, O. Tuzel, S. Ramalingam, and R. Chellappa. Entropy-rate clustering: Cluster analysis via maximizing a submodular function subject to a matroid constraint. PAMI, 36(1):99--112, 2014.
12. S. T. McCormick. Submodular function minimization. Handbooks in operations research and management science, 12:321--391, 2005.
13. G. L. Nemhauser, L. A. Wolsey, and M. L. Fisher. An analysis of approximations for maximizing submodular set functions. Mathematical Programming, 14(1):265--294, 1978.
14. L. Nie, L. Zhang, Y. Yang, M. Wang, R. Hong, and T.-S. Chua. Beyond doctors: future health prediction from multimedia and multimodal observations. In MM, pages 591--600, 2015.
15. K. Ozaki, M. Shimbo, M. Komachi, and Y. Matsumoto. Using the mutual k-nearest neighbor graphs for semi-supervised classification of natural language data. In CoNLL, pages 154--162, 2011.
16. S. J. Pan and Q. Yang. A survey on transfer learning. Knowledge and Data Engineering, IEEE Transactions on, 22(10):1345--1359, 2010.
17. X. Shi, Q. Liu, W. Fan, and P. S. Yu. Transfer across completely different feature spaces via spectral embedding. Knowledge and Data Engineering, IEEE Transactions on, 25(4):906--918, 2013.
18. X. Song, L. Nie, L. Zhang, M. Liu, and T.-S. Chua. Interest inference via structure-constrained multi-source multi-task learning. In IJCAI, pages 2371--2377, 2015.
19. N. Srivastava and R. R. Salakhutdinov. Multimodal learning with deep boltzmann machines. In NIPS, pages 2222--2230, 2012.
20. B. Tan, E. Zhong, E. W. Xiang, and Q. Yang. Multi-transfer: Transfer learning with multiple views and multiple sources. In SDM, 2013.
21. Y. Wei, Y. Song, Y. Zhen, B. Liu, and Q. Yang. Scalable heterogeneous translated hashing. In SIGKDD, pages 791--800, 2014.
22. Y. Wei, Y. Zhu, C. W.-k. Leung, Y. Song, and Q. Yang. Instilling social to physical: Co-regularized heterogeneous transfer learning. In AAAI, 2016.
23. D. Yang, D. Zhang, Z. Yu, and Z. Yu. Fine-grained preference-aware location search leveraging crowdsourced digital footprints from LBSNs. In UbiComp, pages 479--488, 2013.
24. H. Yang and J. He. Learning with dual heterogeneity: a nonparametric bayes model. In SIGKDD, pages 582--590, 2014.
25. P. Yang and W. Gao. Multi-view discriminant transfer learning. In IJCAI, pages 1848--1854, 2013.
26. P. Yang, W. Gao, Q. Tan, and K.-F. Wong. Information-theoretic multi-view domain adaptation. In ACL, pages 270--274, 2012.
27. P. Yang and J. He. Model Multiple Heterogeneity via Hierarchical Multi-Latent Space Learning. In SIGKDD, pages 1375--1384, 2015.
28. Q. Yang, Y. Chen, G.-R. Xue, W. Dai, and Y. Yu. Heterogeneous transfer learning for image clustering via the social web. In ACL, pages 1--9, 2009.
29. Z. Yu, F. Wu, Y. Yang, Q. Tian, J. Luo, and Y. Zhuang. Discriminative coupled dictionary hashing for fast cross-media retrieval. In SIGIR, pages 395--404, 2014.
30. D. Zhang, J. He, Y. Liu, L. Si, and R. Lawrence. Multi-view transfer learning with a large margin approach. In SIGKDD, pages 1208--1216, 2011.
31. J. Zhang and J. Huan. Inductive multi-task learning with multiple view data. In SIGKDD, pages 543--551, 2012.
32. Z. Y. Zhao, M. Xie, and M. West. Dynamic dependence networks: Financial time series forecasting and portfolio decisions. Applied Stochastic Models in Business and Industry, 2016.
33. Y. Zheng, L. Capra, O. Wolfson, and H. Yang. Urban computing: concepts, methodologies, and applications. ACM Transactions on Intelligent Systems and Technology (TIST), 5(3):38, 2014.
34. Y. Zheng, F. Liu, and H.-P. Hsieh. U-air: When urban air quality inference meets big data. In SIGKDD, pages 1436--1444, 2013.
35. Y. Zheng, T. Liu, Y. Wang, Y. Zhu, Y. Liu, and E. Chang. Diagnosing new york city's noises with ubiquitous data. In UbiComp, pages 715--725, 2014.
36. Y. Zheng, X. Yi, M. Li, R. Li, Z. Shan, E. Chang, and T. Li. Forecasting Fine-Grained Air Quality Based on Big Data. In SIGKDD, pages 2267--2276, 2015.

Index Terms

• Computing methodologies

  • Machine learning

    • Learning paradigms

      • Multi-task learning

        • Transfer learning

• Information systems

  • Information systems applications

    • Data mining

    • Spatial-temporal systems

      • Geographic information systems