Social recommendation using Euclidean embedding

Li, Wentao; Gao, Min; Rong, Wenge; Wen, Junhao; Xiong, Qingyu; Jia, Ruixi; Dou, Tong

doi:10.1109/ijcnn.2017.7965906

Cited by 22 publications

(6 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, there rises a new trend in the community to alleviate the intrinsic problem of MF-based algorithms [27], [55], [56]. Among them, a popular idea is to borrow the strengths of metric learning [57], [58], due to its simplicity and effectiveness [39], [59], [60], [61], [62]. Noteworthy is the work known as Collaborative Metric Learning (CML) [24], which is the first successful integration of metric learning and CF.…”

Section: One-class Collaborative Filteringmentioning

confidence: 99%

Rethinking Collaborative Metric Learning: Toward an Efficient Alternative Without Negative Sampling

Bao

Yang

et al. 2023

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

The recently proposed Collaborative Metric Learning (CML) paradigm has aroused wide interest in the area of recommendation systems (RS) owing to its simplicity and effectiveness. Typically, the existing literature of CML depends largely on the negative sampling strategy to alleviate the time-consuming burden of pairwise computation. However, in this work, by taking a theoretical analysis, we find that negative sampling would lead to a biased estimation of the generalization error. Specifically, we show that the samplingbased CML would introduce a bias term in the generalization bound, which is quantified by the per-user Total Variance (TV) between the distribution induced by negative sampling and the ground truth distribution. This suggests that optimizing the sampling-based CML loss function does not ensure a small generalization error even with sufficiently large training data. Moreover, we show that the bias term will vanish without the negative sampling strategy. Motivated by this, we propose an efficient alternative without negative sampling for CML named Sampling-Free Collaborative Metric Learning (SFCML), to get rid of the sampling bias in a practical sense. Finally, comprehensive experiments over seven benchmark datasets speak to the superiority of the proposed algorithm.

show abstract

Section: One-class Collaborative Filteringmentioning

confidence: 99%

Rethinking Collaborative Metric Learning: Toward an Efficient Alternative Without Negative Sampling

Bao

Yang

et al. 2023

IEEE Trans. Pattern Anal. Mach. Intell.

View full text Add to dashboard Cite

show abstract

“…Metric learning has been introduced into the recommendation domain to address this issue. Li et al [28] directly used metric learning to replace the dot product of user and item features, and thus proposed the SREE algorithm to integrate user similarity information when predicting ratings. The predictive rating formula is as follows:…”

Section: Related Workmentioning

confidence: 99%

User Bias Drift Social Recommendation Algorithm based on Metric Learning

2022

KSII TIIS

View full text Add to dashboard Cite

Social recommendation algorithm can alleviate data sparsity and cold start problems in recommendation system by integrated social information. Among them, matrix-based decomposition algorithms are the most widely used and studied. Such algorithms use dot product operations to calculate the similarity between users and items, which ignores user's potential preferences, reduces algorithms' recommendation accuracy. This deficiency can be avoided by a metric learning-based social recommendation algorithm, which learns the distance between user embedding vectors and item embedding vectors instead of vector dotproduct operations. However, previous works provide no theoretical explanation for its plausibility. Moreover, most works focus on the indirect impact of social friends on user's preferences, ignoring the direct impact on user's rating preferences, which is the influence of user rating preferences. To solve these problems, this study proposes a user bias drift social recommendation algorithm based on metric learning (BDML). The main work of this paper is as follows: (1) the process of introducing metric learning in the social recommendation scenario is introduced in the form of equations, and explained the reason why metric learning can replace the click operation; (2) a new user bias is constructed to simultaneously model the impact of social relationships on user's ratings preferences and user's preferences; Experimental results on two datasets show that the BDML algorithm proposed in this study has better recommendation accuracy compared with other comparison algorithms, and will be able to guarantee the recommendation effect in a more sparse dataset.

show abstract

“…(2) Social network-based methods, including GraphRec [4], DeepFM+ [7], SocialMF [12], SREE [16] and SoReg [19]. (3) Propensity-based methods, including CausE [1] and D-WMF [36].…”

Section: Datasetsmentioning

confidence: 99%

“…For fair comparison, a grid search is conducted to choose the optimal parameter settings, e.g., dimension of user/item latent vector 𝑘 𝑀𝐹 for matrix factorization-based models and dimension of embedding vector 𝑑 for neural network-based models. The embedding size is initialized with the Xavier [5] and searched in [8,16,32,64,128,256].…”

Section: Datasetsmentioning

confidence: 99%

“…Without specification, unique hyperparameters of DENC are set as: three coefficients 𝜆 𝑛 , 𝜆 𝑢 and 𝜆 𝑖 are tuned in {10 −3 , 10 −4 , 10 −5 }. The dimension of node2vec embedding size 𝑘 𝑎 and the dimension of inherent factor 𝑘 𝑑 are tuned in [8,16,32,64,128,256], and their influences are reported in Section 4.4.…”

Section: Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

Be Causal: De-biasing Social Network Confounding in Recommendation

Li¹,

Wang²,

Xu³

2021

Preprint

View full text Add to dashboard Cite

In recommendation systems, the existence of the missing-not-atrandom (MNAR) problem results in the selection bias issue, degrading the recommendation performance ultimately. A common practice to address MNAR is to treat missing entries from the socalled "exposure" perspective, i.e., modeling how an item is exposed (provided) to a user. Most of the existing approaches use heuristic models or re-weighting strategy on observed ratings to mimic the missing-at-random setting. However, little research has been done to reveal how the ratings are missing from a causal perspective. To bridge the gap, we propose an unbiased and robust method called DENC (De-bias Network Confounding in Recommendation) inspired by confounder analysis in causal inference. In general, DENC provides a causal analysis on MNAR from both the inherent factors (e.g., latent user or item factors) and auxiliary network's perspective. Particularly, the proposed exposure model in DENC can control the social network confounder meanwhile preserves the observed exposure information. We also develop a deconfounding model through the balanced representation learning to retain the primary user and item features, which enables DENC generalize well on the rating prediction. Extensive experiments on three datasets validate that our proposed model outperforms the state-of-the-art baselines.

show abstract

Social recommendation using Euclidean embedding

Cited by 22 publications

References 21 publications

Rethinking Collaborative Metric Learning: Toward an Efficient Alternative Without Negative Sampling

Rethinking Collaborative Metric Learning: Toward an Efficient Alternative Without Negative Sampling

User Bias Drift Social Recommendation Algorithm based on Metric Learning

Be Causal: De-biasing Social Network Confounding in Recommendation

Contact Info

Product

Resources

About