Coupling learning of complex interactions

IEEE Trans. Knowl. Data Eng.

Liu

et al. 2018

Self Cite

Learning appropriate metric is critical for effectively capturing complex data characteristics. The metric learning of categorical data with hierarchical coupling relationships and local heterogeneous distributions is very challenging yet rarely explored. This paper proposes a Heterogeneous mEtric Learning with hIerarchical Couplings, HELIC, for this type of categorical data. HELIC captures both low-level value-to-attribute and high-level attribute-to-class hierarchical couplings, and reveals the intrinsic heterogeneities embedded in each level of couplings. Theoretical analyses of the effectiveness and generalization error bound verify that HELIC effectively represents the above complexities. Extensive experiments on 30 data sets with diverse characteristics demonstrate that HELIC-enabled classification significantly enhances the accuracy (up to 40.93%), compared with five state-of-the-art baselines.

Section: Related Workmentioning

confidence: 99%

Heterogeneous Metric Learning of Categorical Data with Hierarchical Couplings

Zhu

IEEE Trans. Knowl. Data Eng.

Liu

et al. 2018

Self Cite

“…The hidden user-item interactions in Table D have not been explored in the relevant community, although they are very important for a deep understanding of how and why ratings are generated. The interactions in Table D are not as visible as those in other tables, but they incorporate implicit relations (which here we call coupling [6]) between a user attribute and an item property. (See more discussions in Section 6.5.…”

Section: Nature Of Recommendationmentioning

confidence: 99%

“…Such a non-IID recommendation perspective opens paradigm-shifting opportunities and new directions for next-generation foundational research and quality recommendation. In fact, learning non-IIDness [5,6] in big data is a foundational theoretical and practical challenge in data science and big data analytics [3,[13][14][15], which has not been paid much attention in relevant communities including computing, informatics, and statistics, because existing analytics and learning theories and systems have been mainly built on the IID assumption. The discussions about non-IID recommendation theories and systems in this work will hopefully inspire fundamental research and promising outcomes in other analytical, learning, and information-processing areas.…”

Section: Introductionmentioning

confidence: 99%

Non-IID Recommender Systems: A Review and Framework of Recommendation Paradigm Shifting

2016

Engineering

Self Cite

While recommendation plays an increasingly critical role in our living, study, work, and entertainment, the recommendations we receive are often for irrelevant, duplicate, or uninteresting products and services. A critical reason for such bad recommendations lies in the intrinsic assumption that recommended users and items are independent and identically distributed (IID) in existing theories and systems. Another phenomenon is that, while tremendous efforts have been made to model specific aspects of users or items, the overall user and item characteristics and their non-IIDness have been overlooked. In this paper, the non-IID nature and characteristics of recommendation are discussed, followed by the non-IID theoretical framework in order to build a deep and comprehensive understanding of the intrinsic nature of recommendation problems, from the perspective of both couplings and heterogeneity. This non-IID recommendation research triggers the paradigm shift from IID to non-IID recommendation research and can hopefully deliver informed, relevant, personalized, and actionable recommendations. It creates exciting new directions and fundamental solutions to address various complexities including cold-start, sparse data-based, cross-domain, group-based, and shilling attack-related issues.

“…Most current recommender systems are built on subjective feedback, e.g., ratings, to differentiate user preferences. However, subjective feedback is not always available, while objective feedback, e.g., click logs, is more easily obtained [Cao 2015]. The implicit preference data is often represented by binary values, that is, 1 for observed choices and 0 for others [Hu et al 2014;Pan et al 2008].…”

Section: Recommender Systemsmentioning

confidence: 99%

Learning Informative Priors from Heterogeneous Domains to Improve Recommendation in Cold-Start User Domains

et al. 2016

ACM Trans. Inf. Syst.

Self Cite

In the real-world environment, users have sufficient experience in their focused domains but lack experience in other domains. Recommender systems are very helpful for recommending potentially desirable items to users in unfamiliar domains, and cross-domain collaborative filtering is therefore an important emerging research topic. However, it is inevitable that the cold-start issue will be encountered in unfamiliar domains due to the lack of feedback data. The Bayesian approach shows that priors play an important role when there are insufficient data, which implies that recommendation performance can be significantly improved in cold-start domains if informative priors can be provided. Based on this idea, we propose a Weighted Irregular Tensor Factorization (WITF) model to leverage multi-domain feedback data across all users to learn the cross-domain priors w.r.t. both users and items. The features learned from WITF serve as the informative priors on the latent factors of users and items in terms of weighted matrix factorization models. Moreover, WITF is a unified framework for dealing with both explicit feedback and implicit feedback. To prove the effectiveness of our approach, we studied three typical real-world cases in which a collection of empirical evaluations were conducted on real-world datasets to compare the performance of our model and other state-of-the-art approaches. The results show the superiority of our model over comparison models.