A Hierarchical Self-Attentive Model for Recommending User-Generated Item Lists

He, Yun; Wang, Jianling; Niu, Wei; Caverlee, James

doi:10.1145/3357384.3358030

Cited by 31 publications

(11 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We apply grid search for tuning the hyper-parameters of the models: the learning rate is tuned amongst {0.0001, 0.0005, 0.001, 0.005, 0.01}, the coefficient of 2 regularization is searched in {10 −5 , 10 −4 , ..., 1, 10 1 }, and the dropout ratio in {0.0, 0.1, ..., 0.5}. The set of possible hyper-parameter 7 https://pytorch.org/ values was determined on early validation tests using subsets of the datasets that we then discarded from our analyses.…”

Section: Methodsmentioning

confidence: 99%

“…Deep Attentive Multi-Task DAM [3] model designs a factorized attention network to aggregate the embeddings of items within a bundle to obtain the bundle's representation, while jointly model user-bundle interactions and user-item interactions in a multi-task manner to alleviate the scarcity of user-bundle interactions. Some other related efforts include [1,5,7,13,15].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Personalized Bundle Recommendation in Online Games

Deng

Wang

Zhao

et al. 2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

In business domains, bundling is one of the most important marketing strategies to conduct product promotions, which is commonly used in online e-commerce and offline retailers. Existing recommender systems mostly focus on recommending individual items that users may be interested in. In this paper, we target at a practical but less explored recommendation problem named bundle recommendation, which aims to offer a combination of items to users. To tackle this specific recommendation problem in the context of the virtual mall in online games, we formalize it as a link prediction problem on a user-item-bundle tripartite graph constructed from the historical interactions, and solve it with a neural network model that can learn directly on the graph-structure data. Extensive experiments on three public datasets and one industrial game dataset demonstrate the effectiveness of the proposed method. Further, the bundle recommendation model has been deployed in production for more than one year in a popular online game developed by Netease Games, and the launch of the model yields more than 60% improvement on conversion rate of bundles, and a relative improvement of more than 15% on gross merchandise volume (GMV).

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Personalized Bundle Recommendation in Online Games

Deng

Wang

Zhao

et al. 2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

show abstract

“…In our experiments, as a non-linear network for sessions of any length, we use two-layer point-wise feed-forward networks for the item embeddings in a session and take the average of the outputs as the logits. Also we add a learnable positional embedding [3,6] to each item embedding, which encodes information about its position, in order to model the sequential pattern. That is, the encoder network for proxy selection in our experiments is built as follows:…”

Section: Implementation Detailsmentioning

confidence: 99%

Unsupervised Proxy Selection for Session-based Recommender Systems

Cho

Kang

Hyun

et al. 2021

Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

Session-based Recommender Systems (SRSs) have been actively developed to recommend the next item of an anonymous short item sequence (i.e., session). Unlike sequence-aware recommender systems where the whole interaction sequence of each user can be used to model both the short-term interest and the general interest of the user, the absence of user-dependent information in SRSs makes it difficult to directly derive the user's general interest from data. Therefore, existing SRSs have focused on how to effectively model the information about short-term interest within the sessions, but they are insufficient to capture the general interest of users. To this end, we propose a novel framework to overcome the limitation of SRSs, named ProxySR, which imitates the missing information in SRSs (i.e., general interest of users) by modeling proxies of sessions. ProxySR selects a proxy for the input session in an unsupervised manner, and combines it with the encoded short-term interest of the session. As a proxy is jointly learned with the short-term interest and selected by multiple sessions, a proxy learns to play the role of the general interest of a user and ProxySR learns how to select a suitable proxy for an input session. Moreover, we propose another real-world situation of SRSs where a few users are logged-in and leave their identifiers in sessions, and a revision of ProxySR for the situation. Our experiments on real-world datasets show that ProxySR considerably outperforms the state-of-the-art competitors, and the proxies successfully imitate the general interest of the users without any user-dependent information.

show abstract

“…In practice, due to the occurrence of some extreme samples, L may be set to be extremely large, resulting in the waste of memory space and affecting the speed of training. To tackle this problem, we choose the last L items that the user interacted with before the current session and put their embeddings into the long-term encoder, which is similar as in [37]. In detail, if the number of the historical items H is smaller than L, the last L − H rows of E (u,c) will be filled with 0.…”

Section: User's Long-term Preference Analysismentioning

confidence: 99%

A Joint Neural Network for Session-Aware Recommendation

et al. 2020

View full text Add to dashboard Cite

Session-aware recommendation is a special form of sequential recommendation, where users' previous interactions before current session are available. Recently, Recurrent Neural Network (RNN) based models are widely used in sequential recommendation tasks with great success. Previous works mainly focus on the interaction sequences of the current session without analyzing a user's long-term preferences. In this paper, we propose a joint neural network (JNN) for session-aware recommendation, which employs a Convolutional Neural Network(CNN) and a RNN to process the long-term historical interactions and the short-term sequential interactions respectively. Then, we apply a fully-connected neural network to study the complex relationship between these two types of features, which aims to generate a unified representation of the current session. Finally, a recommendation score for given items is generated by a bi-linear scheme upon the session representation. We conduct our experiments on three public datasets, showing that JNN outperforms the state-of-the-art baselines on all datasets in terms of Recall and Mean Reciprocal Rank (MRR). The outperforming results indicate that proper handling of historical interactions can improve the effectiveness of recommendation. The experimental results show that JNN is more prominent in samples with short current session or long historical interactions. INDEX TERMS Session-aware recommendation, sequential recommendation, recurrent neural networks, convolutional neural networks.

show abstract

A Hierarchical Self-Attentive Model for Recommending User-Generated Item Lists

Cited by 31 publications

References 34 publications

Personalized Bundle Recommendation in Online Games

Personalized Bundle Recommendation in Online Games

Unsupervised Proxy Selection for Session-based Recommender Systems

A Joint Neural Network for Session-Aware Recommendation

Contact Info

Product

Resources

About