Using Adversarial Autoencoders for Multi-Modal Automatic Playlist Continuation

Vagliano, Iacopo; Galke, Lukas; Mai, Florian; Scherp, Ansgar

doi:10.1145/3267471.3267476

Cited by 6 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, the models can also be applied to similar tasks in other domains, which could also benefit of the use of metadata. For example, we have previously shown that metadata are beneficial for automatic playlist continuation [12].…”

Section: Threats To Validitymentioning

confidence: 99%

“…For the latter, the task is for professional indexers to choose representative annotations from a domain-specific thesaurus in order to label scientific papers. The existing body of works is typically concerned with one-off recommendation, e. g., recommendations of scientific collaborators [8], suggestion of which paper or news to read next [1,9,10], or recommending an open sequence of items, e. g., music recommendations on Spotify, which are continuously extended as long as the users are listening [11,12,13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Recommendations for Item Set Completion: On the Semantics of Item Co-Occurrence With Data Sparsity, Input Size, and Input Modalities

Vagliano¹,

Galke²,

Scherp³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

We address the problem of recommending relevant items to a user in order to "complete" a partial set of items already known. We consider the two scenarios of citation and subject label recommendation, which resemble different semantics of item co-occurrence: relatedness for co-citations and diversity for subject labels. We assess the influence of the completeness of an already known partial item set on the recommender performance. We also investigate data sparsity through a pruning parameter, and the influence of using additional metadata. As recommender models, we focus on different autoencoders, which are particularly suited for reconstructing missing items in a set. We extend autoencoders to exploit a multi-modal input of text and structured data. Our experiments on six real-world datasets show that supplying the partial item set as input is helpful when item co-occurrence resembles relatedness, while metadata are effective when co-occurrence implies diversity. This outcome means that the semantics of item co-occurrence is an important factor. The simple item co-occurrence model is a strong baseline for citation recommendation. However, autoencoders have the advantage to enable exploiting additional metadata besides the partial item set as input, and achieve comparable performance. For the subject label recommendation task, the title is the most important attribute. Adding more input modalities sometimes even harms the result. In conclusion, it is crucial to consider the semantics of the item co-occurrence for the choice of an appropriate recommendation model and carefully decide which metadata to exploit.

show abstract

Section: Threats To Validitymentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Recommendations for Item Set Completion: On the Semantics of Item Co-Occurrence With Data Sparsity, Input Size, and Input Modalities

Vagliano¹,

Galke²,

Scherp³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…VAE-AR [66] 2017 ✓ ✓ ✓ RGD-TR [71] 2018 ✓ ✓ ✓ aae-RS [136] 2018 ✓ ✓ ✓ SDNet [26] 2019 ✓ ✓ ✓ ATR [89] 2019 ✓ ✓ ✓ AugCF [127] 2019 ✓ ✓ ✓ RSGAN [138] 2019 ✓ ✓ ✓ RRGAN [24] 2019 ✓ ✓ ✓ UGAN [129] 2019 ✓ ✓ ✓ LARA [107] 2020 ✓ ✓ ✓ CGAN [28] 2020 ✓ ✓ ✓ Context-aware Rec. Temporal-aware RecGAN [8] 2018 ✓ ✓ ✓ NMRN-GAN [126] 2018 ✓ ✓ ✓ AAE [116] 2018 ✓ ✓ ✓ PLASTIC [147] 2018 [25] 2019 ✓ ✓ ✓ Geographical-aware Geo-ALM [75] 2019 ✓ ✓ ✓ APOIR [148] 2019 ✓ ✓ ✓ Cross-domain Rec. VAE-GAN-CC [82] 2018 ✓ ✓ ✓ RecSys-DAN [121] 2019 ✓ ✓ ✓ FR-DiscoGAN [59] 2019 ✓ ✓ ✓ DASO [39] 2019 ✓ ✓ ✓ CnGAN [88] 2019 ✓ ✓ ✓ Fashion Rec.…”

Section: Model Namementioning

confidence: 99%

“…Temporal-aware RecGAN [8] 2018 ✓ ✓ ✓ NMRN-GAN [126] 2018 ✓ ✓ ✓ AAE [116] 2018 ✓ ✓ ✓ PLASTIC [147] 2018 [25] 2019 ✓ ✓ ✓ Geographical-aware Geo-ALM [75] 2019 ✓ ✓ ✓ APOIR [148] 2019 ✓ ✓ ✓ Cross-domain Rec. VAE-GAN-CC [82] 2018 ✓ ✓ ✓ RecSys-DAN [121] 2019 ✓ ✓ ✓ FR-DiscoGAN [59] 2019 ✓ ✓ ✓ DASO [39] 2019 ✓ ✓ ✓ CnGAN [88] 2019 ✓ ✓ ✓ Fashion Rec.…”

Section: Collaborative Recommendationmentioning

confidence: 99%

Adversarial Machine Learning in Recommender Systems (AML-RecSys)

Deldjoo

Noia

Merra

2020

Proceedings of the 13th International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

Latent-factor models (LFM) based on collaborative filtering (CF), such as matrix factorization (MF) and deep CF methods, are widely used in modern recommender systems (RS) due to their excellent performance and recommendation accuracy. Notwithstanding their great success, in recent years, it has been shown that these methods are vulnerable to adversarial examples, i.e., subtle but non-random perturbations designed to force recommendation models to produce erroneous outputs. The main reason for this behavior is that user interaction data used for training of LFM can be contaminated by malicious activities or users' misoperation that can induce an unpredictable amount of natural noise and harm recommendation outcomes. On the other side, it has been shown that these systems, conceived originally to attack machine learning applications, can be successfully adopted to strengthen their robustness against attacks as well as to train more precise recommendation engines.In this respect, the goal of this survey is two-fold: (i) to present recent advances on AML-RS for the security of RS (i.e., attacking and defense recommendation models), (ii) to show another successful application of AML in generative adversarial networks (GANs), which use the core concept of learning in AML (i.e., the min-max game) for generative applications.In this survey, we provide an exhaustive literature review of 60 articles published in major RS and ML journals and conferences. This review serves as a reference for the RS community, working on the security of RS and recommendation models leveraging generative models to improve their quality.

show abstract

“…Clearly there are very significant differences in the two approaches, even though both utilize autoencoders. To delve deeper into these differences and how they might have resulted in such a large difference in scores, we recommend reading both [48] and [53].…”

Section: Other Notable Approachesmentioning

confidence: 99%

An Analysis of Approaches Taken in the ACM RecSys Challenge 2018 for Automatic Music Playlist Continuation

Zamani

Schedl

Lamere³

et al. 2019

ACM Trans. Intell. Syst. Technol.

View full text Add to dashboard Cite

The ACM Recommender Systems Challenge 2018 focused on the task of automatic music playlist continuation, which is a form of the more general task of sequential recommendation. Given a playlist of arbitrary length with some additional meta-data, the task was to recommend up to 500 tracks that fit the target characteristics of the original playlist. For the RecSys Challenge, Spotify released a dataset of one million user-generated playlists. Participants could compete in two tracks, i.e., main and creative tracks. Participants in the main track were only allowed to use the provided training set, however, in the creative track, the use of external public sources was permitted. In total, 113 teams submitted 1,228 runs to the main track; 33 teams submitted 239 runs to the creative track. The highest performing team in the main track achieved an R-precision of 0.2241, an NDCG of 0.3946, and an average number of recommended songs clicks of 1.784. In the creative track, an R-precision of 0.2233, an NDCG of 0.3939, and a click rate of 1.785 was obtained by the best team. This article provides an overview of the challenge, including motivation, task definition, dataset description, and evaluation. We further report and analyze the results obtained by the top performing teams in each track and explore the approaches taken by the winners. We finally summarize our key findings, discuss generalizability of approaches and results to domains other than music, and list the open avenues and possible future directions in the area of automatic playlist continuation.

show abstract

Using Adversarial Autoencoders for Multi-Modal Automatic Playlist Continuation

Cited by 6 publications

References 9 publications

Recommendations for Item Set Completion: On the Semantics of Item Co-Occurrence With Data Sparsity, Input Size, and Input Modalities

Recommendations for Item Set Completion: On the Semantics of Item Co-Occurrence With Data Sparsity, Input Size, and Input Modalities

Adversarial Machine Learning in Recommender Systems (AML-RecSys)

An Analysis of Approaches Taken in the ACM RecSys Challenge 2018 for Automatic Music Playlist Continuation

Contact Info

Product

Resources

About