Robust Factorization Machines for User Response Prediction

Punjabi, Surabhi; Bhatt, Priyanka

doi:10.1145/3178876.3186148

Cited by 21 publications

(17 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The improvements over the state-of-the-art methods have been confirmed to be statistically significant according to the test results. Moreover, by examining the two different robust FM variants (RFM-PB by [14] and our RMF method), we found that both methods improve the performance of vanilla FM for most cases, which validates the advantage of endowing FM model with robustness. However, we notice that the RFM-PB by [14] is not always better than CFM for many cases; and by contrast, our RMF is consistently better than CFM.…”

Section: Results Of Recommendation and Classificationsupporting

confidence: 55%

“…Moreover, by examining the two different robust FM variants (RFM-PB by [14] and our RMF method), we found that both methods improve the performance of vanilla FM for most cases, which validates the advantage of endowing FM model with robustness. However, we notice that the RFM-PB by [14] is not always better than CFM for many cases; and by contrast, our RMF is consistently better than CFM. This encouraging results validate the effectiveness and importance of the proposed doubly capped norms minimization scheme.…”

Section: Results Of Recommendation and Classificationsupporting

confidence: 55%

“…Besides, independent of our study, the same problem setting as robust Factorization Machine has been addressed very recently [14]. The key difference between the proposed method and the method by [14] (named as "RFM-PB" for short) is that they model uncertainty as bounded set based variability in the input signals. For each data point x, it associates uncertainty vector u ∈ R d s.t.|u j | ≤ η j , ∀j ∈ {1, .…”

Section: Robust Factorization Machinementioning

confidence: 99%

“…• RFM-PB: A recent robust Factorization Machine proposed by [14], which models the data uncertainty in the input signals.…”

Section: Baselines and Experimental Setupsmentioning

confidence: 99%

See 3 more Smart Citations

Robust Factorization Machine: A Doubly Capped Norms Minimization

Liu¹,

Zhang²,

Li³

et al. 2019

Proceedings of the 2019 SIAM International Conference on Data Mining

View full text Add to dashboard Cite

Factorization Machine (FM) is a general supervised learning framework for many AI applications due to its powerful capability of feature engineering. Despite being extensively studied, existing FM methods have several limitations in common. First of all, most existing FM methods often adopt the squared loss in the modeling process, which can be very sensitive when the data for learning contains noises and outliers. Second, some recent FM variants often explore the low-rank structure of the feature interactions matrix by relaxing the low-rank minimization problem as a trace norm minimization, which cannot always achieve a tight approximation to the original one. To address the aforementioned issues, this paper proposes a new scheme of Robust Factorization Machine (RFM) by exploring a doubly capped norms minimization approach, which employs both a capped squared trace norm in achieving a tighter approximation of the rank minimization and a capped 1norm loss to enhance the robustness of the empirical loss minimization from noisy data. We develop an efficient algorithm with a rigorous convergence proof of RFM. Experiments on public real-world datasets show that our method outperforms the state-of-the-art FM methods significantly.

show abstract

Section: Results Of Recommendation and Classificationsupporting

confidence: 55%

Section: Results Of Recommendation and Classificationsupporting

confidence: 55%

Section: Robust Factorization Machinementioning

confidence: 99%

“…• RFM-PB: A recent robust Factorization Machine proposed by [14], which models the data uncertainty in the input signals.…”

Section: Baselines and Experimental Setupsmentioning

confidence: 99%

See 2 more Smart Citations

Robust Factorization Machine: A Doubly Capped Norms Minimization

Liu¹,

Zhang²,

Li³

et al. 2019

Proceedings of the 2019 SIAM International Conference on Data Mining

View full text Add to dashboard Cite

show abstract

“…The improvements achieved by these models show that explicit interaction between variables is important for advertisement performance prediction, so we adopted explicit interaction in our idea as a conditional attention mechanism. There are several studies on CVR prediction [27,29,39], but there are not as many as the studies on CTR prediction. CVR prediction is difficult, because the number of conversions is imbalanced data that almost ad creative's conversions are zero.…”

Section: Ctr and Conversion Prediction In Display Advertisingmentioning

confidence: 99%

Conversion Prediction Using Multi-task Conditional Attention Networks to Support the Creation of Effective Ad Creatives

Kitada

Iyatomi

Seki³

2019

Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

Accurately predicting conversions in advertisements is generally a challenging task, because such conversions do not occur frequently. In this paper, we propose a new framework to support creating high-performing ad creatives, including the accurate prediction of ad creative text conversions before delivering to the consumer. The proposed framework includes three key ideas: multi-task learning, conditional attention, and attention highlighting. Multi-task learning is an idea for improving the prediction accuracy of conversion, which predicts clicks and conversions simultaneously, to solve the difficulty of data imbalance. Furthermore, conditional attention focuses attention of each ad creative with the consideration of its genre and target gender, thus improving conversion prediction accuracy. Attention highlighting visualizes important words and/or phrases based on conditional attention. We evaluated the proposed framework with actual delivery history data (14,000 creatives displayed more than a certain number of times from Gunosy Inc.), and confirmed that these ideas improve the prediction performance of conversions, and visualize noteworthy words according to the creatives' attributes.

show abstract

A Three-Step Method for Audience Extension in Internet Advertising Using an Industrial Taxonomy

Frolov,

Taran

2012

Springer Optimization and Its Applications

View full text Add to dashboard Cite

Robust Factorization Machines for User Response Prediction

Cited by 21 publications

References 3 publications

Robust Factorization Machine: A Doubly Capped Norms Minimization

Robust Factorization Machine: A Doubly Capped Norms Minimization

Conversion Prediction Using Multi-task Conditional Attention Networks to Support the Creation of Effective Ad Creatives

A Three-Step Method for Audience Extension in Internet Advertising Using an Industrial Taxonomy

Contact Info

Product

Resources

About