[1906.08511] From Zero-Shot Learning to Cold-Start Recommendationopen searchopen navigation menucontact arXivsubscribe to arXiv mailings

Zero-shot learning (ZSL) and cold-start recommendation (CSR) are two challenging problems in computer vision and recommender system, respectively. In general, they are independently investigated in different communities. This paper, however, reveals that ZSL and CSR are two extensions of the same intension. Both of them, for instance, attempt to predict unseen classes and involve two spaces, one for direct feature representation and the other for supplementary description. Yet there is no existing approach which addresses CSR from the ZSL perspective. This work, for the first time, formulates CSR as a ZSL problem, and a tailor-made ZSL method is proposed to handle CSR. Specifically, we propose a Low-rank Linear Auto-Encoder (LLAE), which challenges three cruxes, i.e., domain shift, spurious correlations and computing efficiency, in this paper. LLAE consists of two parts, a low-rank encoder maps user behavior into user attributes and a symmetric decoder reconstructs user behavior from u

Date: 2020/09/17 09:52

Related Entries

Read more Bayesian Deep Learning Workshop | NIPS 2018
8 users, 7 mentions 2018/12/03 05:30
Read more 不均衡データへの決定打となるか!?「Affinity loss」の論文を読む、実装する - QiitaQiita
54 users, 34 mentions 2019/02/05 14:18
Read more CNNの精度向上手法のモデルサイズによる効果の違いを調べてみた - 終末 A.I.
11 users, 10 mentions 2019/09/15 10:23
Read more beta-VAE: Learning Basic Visual Concepts with a Constrained Variational Framework | OpenReview
2 users, 1 mentions 2019/09/25 15:48
Read more [2008.10242] When Inverse Propensity Scoring does not Work: Affine Corrections for Unbiased Learning...
0 users, 1 mentions 2020/09/03 05:21