Shared Neural Item Representations for Completely Cold Start Problem

Raziperchikolaei, Ramin; Liang, Guannan; Chung, Youngjoo

doi:10.1145/3460231.3474228

Cited by 5 publications

(27 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…While this approach might be effective in recommending items with similar features, we believe this over-constrained setting is limited beyond item features. As pointed in previous study [15], a user who only reads news in sports may still be interested in news on crime, which we believe the method in [18] with tightly coupled towers under performs.…”

Section: Introductionsupporting

confidence: 52%

“…The recently introduced method [18] based on this two-tower RS has further improved the performance for item coldstart recommendation. In [18], the item representation was directly shared into the user encoder in an attempt to better unify the two representations, which achieved state-of-theart results for item cold-start recommendation. While this approach might be effective in recommending items with similar features, we believe this over-constrained setting is limited beyond item features.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Flexible Two-Tower Model for Item Cold-Start Recommendation

Lee,

Cho

2023

IEEE Access

View full text Add to dashboard Cite

One of the main challenges in recommendation system is the item cold-start problem, where absence of historical interactions or ratings in new items makes recommendation difficult. In order to solve the cold-start problem, hybrid neural network models using meta data of the item as a feature is widely used. However, existing cold-start models tend to focus too much on utilizing the side information of items, which may not be flexible enough to capture the interaction information of users. In this study, we propose a flexible framework for better capturing the interaction information of users. Specifically, we incorporate the multiple choice learning scheme into the two-tower neural network which is a popular recommendation model that consists of two towers -one for users and one for items. In our proposed framework, we construct two encoders. One of the two encoders, the tightly-coupled encoder, focuses on the side information of items with which the user has interacted, the other one, loosely-coupled encoder, focuses the user's interaction information. We utilize Gumbel-Softmax to stochastically select the encoder, enhancing the flexibility that considers not only item feature but also user interaction information. We evaluate our proposed framework on two datasets -the MLIMDb dataset which is a combination of widely used the MovieLens and IMDb datasets based on common movies, and the CiteULike dataset. The experimental results show that our proposed framework achieves state-of-the-art results on cold-start recommendation. In the Recall@150 experiments on the CiteULike dataset, we achieved improvement of approximately 2.7% compared to the base model. In the Recall@150 experiments on the MLIMDb dataset, we achieved improvement of approximately 5.2% compared to the base model. We further show our proposed model improves the performance in the warmstart settings. In the Recall@100 experiments on the Citeulike dataset, we observed an improvement of approximately 1.3% compared to the base model. In the Recall@100 experiments on the MLIMDb dataset, we observed an improvement of approximately 3.9% compared to the base model. Our proposed framework provides a flexible approach for capturing the diverse aspects of users in recommendation systems, even for cold-start items. As demonstrated through extensive experiments, our proposed model outperforms several state-of-the-art models on both datasets.

show abstract

Section: Introductionsupporting

confidence: 52%

Section: Introductionmentioning

confidence: 99%

A Flexible Two-Tower Model for Item Cold-Start Recommendation

Lee,

Cho

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Recent studies [7], [28] suggest that using dynamic parameters in the neural network can improve the recommendation in the cold-start problem. CMML [7] uses weight modulation in the last layer of the neural network to decrease the impact of insignificant features from the previous layer.…”

Section: B Parameter Generation For the Cold-start Problem And Hypern...mentioning

confidence: 99%

“…CMML [7] uses weight modulation in the last layer of the neural network to decrease the impact of insignificant features from the previous layer. Raziperchikolaei et al used dynamic parameters generated from items to handle the item cold-start problem [28]. In these works, only a portion of the parameters in the neural network that predicts item scores is generated.…”

Section: B Parameter Generation For the Cold-start Problem And Hypern...mentioning

confidence: 99%

HyperRS: Hypernetwork-Based Recommender System for the User Cold-Start Problem

Nakamura

Ichise

2023

IEEE Access

View full text Add to dashboard Cite

Meta-learning has been proven to be effective for the cold-start problem of recommender systems. Many meta-learning recommender systems that are designed for the user cold-start problem are gradient-based. They use a global parameter learned from existing users to initialize the recommender system parameter for new users that provides a personalized recommendation with limited user-item interactions. Many systems require users' demographic information to learn the global parameter. This requirement raises privacy concerns, and demographic information is not always available. In addition, some of the gradient-based systems need dozens or even hundreds of user-item interactions from existing users to learn the global parameter. This requirement is difficult to satisfy in specific scenarios in which active users and their item interactions are rare. Moreover, gradient-based meta-learning systems rarely capture user preferences over different item attributes, as updating the corresponding weights requires many optimization steps. We proposed HyperRS, a Hypernetwork-based Recommender System, for the user cold-start problem. Our system does not rely on demographic information to provide personalized recommendations. In our system, a hypernetwork generates all weights in the underlying recommender system. The hypernetwork enables the weights to adapt quickly to capture user interest in both item attributes and the contents of the item attributes. The experimental results show that our method outperforms several state-of-the-art meta-learning recommender systems for the user cold-start problem.

show abstract

“…However, a separate neural model needs to be trained to obtain the cold-start embeddings, which limits the scalability of the solution. Raziperchikolaei et al [22] and Zheng et al [45] suggest hybrid and metadata-aware recommendation models to predict implicit feedback for cold-start items of users, respectively. However, those models are not designed for the session-based recommendation setting.…”

Section: Related Workmentioning

confidence: 99%

M2TRec: Metadata-aware Multi-task Transformer for Large-scale and Cold-start free Session-based Recommendations

Shalaby

Afsharinejad

et al. 2022

Proceedings of the 16th ACM Conference on Recommender Systems

View full text Add to dashboard Cite

Session-based recommender systems (SBRSs) have shown superior performance over conventional methods. However, they show limited scalability on large-scale industrial datasets since most models learn one embedding per item. This leads to a large memory requirement (of storing one vector per item) and poor performance on sparse sessions with cold-start or unpopular items. Using one public and one large industrial dataset, we experimentally show that state-of-the-art SBRSs have low performance on sparse sessions with sparse items. We propose M2TRec, a Metadata-aware Multitask Transformer model for session-based recommendations. Our proposed method learns a transformation function from item metadata to embeddings, and is thus, item-ID free (i.e., does not need to learn one embedding per item). It integrates item metadata to learn shared representations of diverse item attributes. During inference, new or unpopular items will be assigned identical representations for the attributes they share with items previously observed during training, and thus will have similar representations with those items, enabling recommendations of even cold-start and sparse items. Additionally, M2TRec is trained in a multi-task setting to predict the next item in the session along with its primary category and subcategories. Our multi-task strategy makes the model converge faster and significantly improves the overall performance. Experimental results show significant performance gains using our proposed approach on sparse items on the two datasets.

show abstract

Shared Neural Item Representations for Completely Cold Start Problem

Cited by 5 publications

References 23 publications

A Flexible Two-Tower Model for Item Cold-Start Recommendation

A Flexible Two-Tower Model for Item Cold-Start Recommendation

HyperRS: Hypernetwork-Based Recommender System for the User Cold-Start Problem

M2TRec: Metadata-aware Multi-task Transformer for Large-scale and Cold-start free Session-based Recommendations

Contact Info

Product

Resources

About