Rethinking Item Importance in Session-based Recommendation

Pan, Zhipeng; Cai, Fei; Ling, Yanxiang; Rijke, Maarten de

doi:10.1145/3397271.3401274

Cited by 44 publications

(16 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The hyper parameters are selected on the validation set which is randomly selected from the training set with a proportion of 10%. Following [7,18,34], the batch size is set to 100 and the dimension of item embeddings is 256. We adopt the Adam optimizer with an initial learning rate 1 −3 and a decay factor 0.1 for every 3 epochs.…”

Section: Methodsmentioning

confidence: 99%

“…For instance, Liu et al [16] apply an attention mechanism to obtain a user's general preference and recent interest relying on the long-term and short-term memories in the current session, respectively. Moreover, in order to better distinguish the importance of items and avoid potential bias brought by unrelated items, Pan et al [18] propose to measure item importance using an importance extraction module, and consider the global preference and recent interest to make item prediction. Furthermore, for the cases that a user's historical interactions are available, Ying et al [36] propose a two-layer hierarchical attention network that takes both user's long-term and short-term preferences into consideration.…”

Section: Attention Based Modelsmentioning

confidence: 99%

“…The models discussed in this paper are the following: (1) Two traditional methods, i.e., S-POP [2] and FPMC [20]; (2) Three RNN-based methods, i.e., GRU4REC [10], NARM [14] and CSRM [30]; (3) Two attention-based methods, i.e., STAMP [16] and SR-IEM [18]; and (4) Two GNN-based methods, i.e., SR-GNN [34] and NISER+ [7].…”

Section: Model Summarymentioning

confidence: 99%

See 2 more Smart Citations

Star Graph Neural Networks for Session-based Recommendation

Pan

Cai

Chen

et al. 2020

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

Self Cite

141

View full text Add to dashboard Cite

Session-based recommendation is a challenging task. Without access to a user's historical user-item interactions, the information available in an ongoing session may be very limited. Previous work on session-based recommendation has considered sequences of items that users have interacted with sequentially. Such item sequences may not fully capture complex transition relationship between items that go beyond inspection order. Thus graph neural network (GNN) based models have been proposed to capture the transition relationship between items. However, GNNs typically propagate information from adjacent items only, thus neglecting information from items without direct connections. Importantly, GNN-based approaches often face serious overfitting problems.We propose Star Graph Neural Networks with Highway Networks (SGNN-HN) for session-based recommendation. The proposed SGNN-HN applies a star graph neural network (SGNN) to model the complex transition relationship between items in an ongoing session. To avoid overfitting, we employ highway networks (HN) to adaptively select embeddings from item representations. Finally, we aggregate the item embeddings generated by the SGNN in an ongoing session to represent a user's final preference for item prediction. Experiments on two public benchmark datasets show that SGNN-HN can outperform state-of-the-art models in terms of P@20 and MRR@20 for session-based recommendation. CCS CONCEPTS• Information systems → Recommender systems.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Attention Based Modelsmentioning

confidence: 99%

See 1 more Smart Citation

Star Graph Neural Networks for Session-based Recommendation

Pan

Cai

Chen

et al. 2020

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

Self Cite

141

View full text Add to dashboard Cite

show abstract

“…For sequential recommendation (ranking) task, The selected baselines include PopRec which ranks items based on popularity, traditional MF-based recommendation models like BPR [33], FPMC [34], TransRec [11]. NARM [20], GRU4Rec [15], Caser [37], SASRec [17], SR-IEM [24] are the DNN based models that are proposed more recently. • Group 4 (Reg).…”

Section: Compared Baselinesmentioning

confidence: 99%

Retrieval & Interaction Machine for Tabular Data Prediction

Qin

Zhang

et al. 2021

Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery &Amp; Data Mining

View full text Add to dashboard Cite

Prediction over tabular data is an essential task in many data science applications such as recommender systems, online advertising, medical treatment, etc. Tabular data is structured into rows and columns, with each row as a data sample and each column as a feature attribute. Both the columns and rows of the tabular data carry useful patterns that could improve the model prediction performance. However, most existing models focus on the cross-column patterns yet overlook the cross-row patterns as they deal with single samples independently. In this work, we propose a general learning framework named Retrieval & Interaction Machine (RIM) that fully exploits both cross-row and cross-column patterns among tabular data. Specifically, RIM first leverages search engine techniques to efficiently retrieve useful rows of the table to assist the label prediction of the target row, then uses feature interaction networks to capture the cross-column patterns among the target row and the retrieved rows so as to make the final label prediction. We conduct extensive experiments on 11 datasets of three important tasks, i.e., CTR prediction (classification), top-recommendation (ranking) and rating prediction (regression). Experimental results show that RIM achieves significant improvements over the state-of-the-art and various baselines, demonstrating the superiority and efficacy of RIM. CCS CONCEPTS• Information systems → Data mining; Users and interactive retrieval.

show abstract

“…Recurrent neural networks (RNNs) [16][17][18] and attention mechanisms [31,32] have been used to model the sequential dependency of items. Recently, graph neural networks (GNNs) [1,13,40,41,50,53,54] have been used to effectively…”

Section: Introductionmentioning

confidence: 99%

S-Walk

Choi

Kim

Lee

et al. 2022

Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

Session-based recommendation (SR) predicts the next items from a sequence of previous items consumed by an anonymous user. Most existing SR models focus only on modeling intra-session characteristics but pay less attention to inter-session relationships of items, which has the potential to improve accuracy. Another critical aspect of recommender systems is computational efficiency and scalability, considering practical feasibility in commercial applications. To account for both accuracy and scalability, we propose a novel session-based recommendation with a random walk, namely S-Walk. Precisely, S-Walk effectively captures intra-and inter-session correlations by handling high-order relationships among items using random walks with restart (RWR). By adopting linear models with closed-form solutions for transition and teleportation matrices that constitute RWR, S-Walk is highly efficient and scalable. Extensive experiments demonstrate that S-Walk achieves comparable or state-of-the-art performance in various metrics on four benchmark datasets. Moreover, the model learned by S-Walk can be highly compressed without sacrificing accuracy, conducting two or more orders of magnitude faster inference than existing DNN-based models, making it suitable for large-scale commercial systems.

show abstract

Rethinking Item Importance in Session-based Recommendation

Cited by 44 publications

References 8 publications

Star Graph Neural Networks for Session-based Recommendation

Star Graph Neural Networks for Session-based Recommendation

Retrieval & Interaction Machine for Tabular Data Prediction

S-Walk

Contact Info

Product

Resources

About