Attention-based Adaptive Model to Unify Warm and Cold Starts Recommendation

Shi, Shaoyun; Zhang, Min; Liu, Yiqun; Ma, Shaoping

doi:10.1145/3269206.3271710

Cited by 51 publications

(56 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…User preferences are expressed as weights. Shi et al (see [28]) used for recommendation a combination of content-based and collaborative filtering, while a method of combining both recommendations was developed via learning the weights of both components from previous prediction accuracy. Cheng et al (see [29]) exploited a matrix factorization model based on reviews and preferences.…”

Section: Recommender Systems For Bimodal Networkmentioning

confidence: 99%

Modeling Bimodal Social Networks Subject to the Recommendation with the Cold Start User-Item Model

Kłopotek

2020

Computers

View full text Add to dashboard Cite

This paper describes the modeling of social networks subject to a recommendation. The Cold Start User-Item Model (CSUIM) of a bipartite graph is considered, which simulates bipartite graph growth based on several parameters. An algorithm is proposed to compute parameters of this model with desired properties. The primary desired property is that the generated graph has similar graph metrics. The next is a change in our graph growth process due to recommendations. The meaning of CSUI model parameters in the recommendation process is described. We make several simulations generating networks from the CSUI model to verify theoretical properties. Also, proposed methods are tested on real-life networks. We prove that the CSUIM model of bipartite graphs is very flexible and can be applied to many different problems. We also show that the parameters of this model can be easily obtained from an unknown bipartite graph.

show abstract

Section: Recommender Systems For Bimodal Networkmentioning

confidence: 99%

Modeling Bimodal Social Networks Subject to the Recommendation with the Cold Start User-Item Model

Kłopotek

2020

Computers

View full text Add to dashboard Cite

show abstract

“…In recent years, many researchers used deep learning methods to solve the cold-start problem in the recommendation systems. The authors [9] proposed a new attention model to unify Collaborative Filtering Recommendation and Content-based Recommendation in both warm and cold scenarios. They proposed a novel cold sampling learning strategy.…”

Section: Related Workmentioning

confidence: 99%

Joint Deep Network With Auxiliary Semantic Learning for Popular Recommendation

2020

View full text Add to dashboard Cite

There is a cold-start problem in the recommendation system field, which is how to profile new users and new items. The popular recommendation algorithm is an important solution to the coldstart problem. In this paper, we propose a new joint deep network model with auxiliary semantic learning for the popular recommendation algorithm (DMPRA). First, we define the items with a large quantity of review data and high ratings as the popular recommended items. Second, we introduce text analysis into the popular recommendation algorithm. We use the optimized CharCNN networks to learn the auxiliary semantic vectors from the users' reviews. Then, we use the Factorization Machine (FM) component and deep component to learn the corresponding vector representations of the items' attribute features. We use convolution to simulate the interaction of hidden latent vectors. This method can make the vectors interact more satisfactorily than traditional interactive representation methods. Finally, we provide the users with a reasonable popular recommendation list. The experimental results show that our algorithm can improve the AUC (area under the ROC curve) and Logloss (cross-entropy) of the popular items' prediction. In addition, we provide relevant explanations for some useful phenomena.

show abstract

“…where c k is the visual representation of image k. Due to the success of convolutional neural networks, similar as many visual modeling approaches, we use the last fully connected layer in VGG-19 to represent the visual content of each image k as c k ∈ R 4096 [Simonyan and Zisserman, 2015;He and McAuley, 2016]. Pc k transforms the original item visual content representation from 4096 dimensions into a low latent visual space, which is usually less than 100 dimensions.…”

Section: The Proposed Modelmentioning

confidence: 99%

Personalized Multimedia Item and Key Frame Recommendation

Chen

Yang

et al. 2019

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

When recommending or advertising items to users, an emerging trend is to present each multimedia item with a key frame image (e.g., the poster of a movie). As each multimedia item can be represented as multiple fine-grained visual images (e.g., related images of the movie), personalized key frame recommendation is necessary in these applications to attract users' unique visual preferences. However, previous personalized key frame recommendation models relied on users' fine-grained image behavior of multimedia items (e.g., user-image interaction behavior), which is often not available in real scenarios. In this paper, we study the general problem of joint multimedia item and key frame recommendation in the absence of the fine-grained user-image behavior. We argue that the key challenge of this problem lies in discovering users' visual profiles for key frame recommendation, as most recommendation models would fail without any users' finegrained image behavior. To tackle this challenge, we leverage users' item behavior by projecting users (items) in two latent spaces: a collaborative latent space and a visual latent space. We further design a model to discern both the collaborative and visual dimensions of users, and model how users make decisive item preferences from these two spaces. As a result, the learned user visual profiles could be directly applied for key frame recommendation. Finally, experimental results on a realworld dataset clearly show the effectiveness of our proposed model on the two recommendation tasks.

show abstract

Attention-based Adaptive Model to Unify Warm and Cold Starts Recommendation

Cited by 51 publications

References 33 publications

Modeling Bimodal Social Networks Subject to the Recommendation with the Cold Start User-Item Model

Modeling Bimodal Social Networks Subject to the Recommendation with the Cold Start User-Item Model

Joint Deep Network With Auxiliary Semantic Learning for Popular Recommendation

Personalized Multimedia Item and Key Frame Recommendation

Contact Info

Product

Resources

About