Exploring Periodicity and Interactivity in Multi-Interest Framework for Sequential Recommendation

Chen, Gaode; Zhang, Xinghua; Zhao, Yanyan; Xue, Cong; Ji, Xiang

doi:10.24963/ijcai.2021/197

Cited by 27 publications

(30 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Subsequently, Cen et al [1] proposed a multi-interest extraction method based on self-attention mechanism (ComiRec-SA) to instead of capsule network. The latest method PIMI [2] introduced the time and periodic information in users' recent interaction sequences into the model. The self-attention mechanism was used to capture users' multi-interests and achieved the state-of-art performance.…”

Section: Related Workmentioning

confidence: 99%

“…Firstly, the sequence length threshold 𝐿 𝑟𝑒𝑐 is set to intercept each user's most recent interactions, which does not include the target item for training. If there are less than 𝐿 𝑟𝑒𝑐 items, the padding strategy [2] will be used. Eventually, each user 𝑢 has a fixed-length…”

Section: Recent Time Interval Representation Modulementioning

confidence: 99%

“…, where 𝑑 is the dimension of embedding. The time interval aware attention mechanism [2] is used to get attention scores S 𝑢 1 ∈ R 𝐿 𝑟𝑒𝑐 ×𝐿 𝑟𝑒𝑐 for each time interval in the sequence, denoted as…”

Section: Recent Time Interval Representation Modulementioning

confidence: 99%

“…The statistics of the datasets are listed in Table 1. We maintained the dataset division in the model validation of ComiRec [1] and PIMI [2]. In detail, we divided each dataset into a training set, a validation set, and a test set at a ratio of 8:1:1.…”

Section: Experiments Settingsmentioning

confidence: 99%

“…The main effort of sequential recommendation is to learn the representations of users and items. Since the interests of users are usually diverse and difficult to be represented by a single low-dimensional vector, the sequential recommendation methods based on multi-interest framework have emerged [1,2,13]. In these methods, the number of representation vectors for each user is increased from 1 to K, where each vector represents one interest of the user.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

GIMIRec: Global Interaction Information Aware Multi-Interest Framework for Sequential Recommendation

Zhang¹,

Chen²,

Chen³

2021

Preprint

View full text Add to dashboard Cite

Sequential recommendation based on multi-interest framework models the user's recent interaction sequence into multiple different interest vectors, since a single low-dimensional vector cannot fully represent the diversity of user interests. However, most existing models only intercept users' recent interaction behaviors as training data, discarding a large amount of historical interaction sequences. This may raise two issues. On the one hand, data reflecting multiple interests of users is missing; on the other hand, the co-occurrence between items in historical user-item interactions is not fully explored. To tackle the two issues, this paper proposes a novel sequential recommendation model called " Global Interaction Aware Multi-Interest Framework for Sequential Recommendation (GIMIRec)". Specifically, a global context extraction module is firstly proposed without introducing any external information, which calculates a weighted co-occurrence matrix based on the constrained co-occurrence number of each item pair and their time interval from the historical interaction sequences of all users and then obtains the global context embedding of each item by using a simplified graph convolution. Secondly, the time interval of each item pair in the recent interaction sequence of each user is captured and combined with the global context item embedding to get the personalized item embedding. Finally, a self-attention based multi-interest framework is applied to learn the diverse interests of users for sequential recommendation. Extensive experiments on the three real-world datasets of Amazon-Books, Taobao-Buy and Amazon-Hybrid show that the performance of GIMIRec on the Recall, NDCG and Hit Rate indicators is significantly superior to that of the state-of-the-art methods. Moreover, the proposed global context extraction module can be easily transplanted to most sequential recommendation models.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Recent Time Interval Representation Modulementioning

confidence: 99%

Section: Recent Time Interval Representation Modulementioning

confidence: 99%

Section: Experiments Settingsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

GIMIRec: Global Interaction Information Aware Multi-Interest Framework for Sequential Recommendation

Zhang¹,

Chen²,

Chen³

2021

Preprint

View full text Add to dashboard Cite

show abstract

Improving Sequential Recommendation with Global Item Transitions and Local Subsequences

Deng,

2023

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

Many recent sequential recommendation methods have aimed to enhance the modeling of users' diverse interests to provide more accurate and varied recommendations. Despite great success, existing models possess a limitation in their capacity to solely perceive items within a user behavior sequence. Such an approach may potentially constrain their ability to effectively discover users' multiple interests. In this paper, we present a novel approach that addresses this gap by harnessing global item transitions to uncover users' potential interests, subsequently modeling them as local subsequences. To achieve this objective, we represent global item transitions as a directed graph, constructed by amalgamating behavior sequences from the training set. This graph‐based representation allows the design of a specialized module capable of aggregating global item transitional information and uncovering local subsequences specific to individual users. Consequently, downstream sequence models can focus on pertinent item transitions, disregarding unrelated ones. We evaluate the effectiveness of our method on four public data sets, outperforming existing alternatives or delivering competitive results. © 2023 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC.

show abstract

Filter-Enhanced Multi-interest Network for Sequential Recommendation

Cui,

Peng,

Chu

et al. 2024

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Exploring Periodicity and Interactivity in Multi-Interest Framework for Sequential Recommendation

Cited by 27 publications

References 15 publications

GIMIRec: Global Interaction Information Aware Multi-Interest Framework for Sequential Recommendation

GIMIRec: Global Interaction Information Aware Multi-Interest Framework for Sequential Recommendation

Improving Sequential Recommendation with Global Item Transitions and Local Subsequences

Filter-Enhanced Multi-interest Network for Sequential Recommendation

Contact Info

Product

Resources

About