A fairness-aware graph contrastive learning recommender framework for social tagging systems

Xu, Can; Zhang, Yin; Chen, Hongyang; Dong, Ligang; Wang, Weigang

doi:10.1016/j.ins.2023.119064

Cited by 18 publications

(10 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It can also be found that BatchSampler can reduce variance in most cases, showing that the exploited hard negatives can enforce the model to learn more robust representations. We also compare BatchSampler with 11 graph classification models including the unsupervised graph learning methods [54,57], graph kernel methods [41,55], and self-supervised graph learning methods [19,34,38,43,53,58,59] (See Appendix B.3).…”

Section: Resultsmentioning

confidence: 99%

“…As for graphs, DGI [37] and InfoGraph [43] treat the node representations and corresponding graph representations as positive pairs. Besides, InfoGCL [53], JOAO [58], GCA [68], GCC [38] and GraphCL [59] augment the graph data by graph sampling or proximity-oriented methods. MVGRL [19] proposes to compare the node representation in one view with the graph representation in the other view.…”

Section: Related Workmentioning

confidence: 99%

“…In Table 10, we comprehensively compare different kinds of baselines on graph classification tasks, including the unsupervised graph learning methods [54,57], graph kernel methods [41,55], and selfsupervised graph learning methods [19,34,38,43,53,58,59]. It can be found that InfoGCL achieves state-the-of-art performance among the self-supervised methods, and even outperforms the supervised methods on some datasets.…”

Section: B3 Comparison With Baselines On Graphsmentioning

confidence: 99%

See 2 more Smart Citations

BatchSampler: Sampling Mini-Batches for Contrastive Learning in Vision, Language, and Graphs

Yang

Ming

Dong

et al. 2023

Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

In-Batch contrastive learning is a state-of-the-art self-supervised method that brings semantically-similar instances close while pushing dissimilar instances apart within a mini-batch. Its key to success is the negative sharing strategy, in which every instance serves as a negative for the others within the mini-batch. Recent studies aim to improve performance by sampling hard negatives within the current mini-batch, whose quality is bounded by the mini-batch itself. In this work, we propose to improve contrastive learning by sampling mini-batches from the input data. We present BatchSampler 1 to sample mini-batches of hard-to-distinguish (i.e., hard and true negatives to each other) instances. To make each mini-batch have fewer false negatives, we design the proximity graph of randomly-selected instances. To form the mini-batch, we leverage random walk with restart on the proximity graph to help sample hard-to-distinguish instances. BatchSampler is a simple and general technique that can be directly plugged into existing contrastive learning models in vision, language, and graphs. Extensive experiments on datasets of three modalities show that BatchSampler can consistently improve the performance of powerful contrastive models, as shown by significant improvements of SimCLR on ImageNet-100, SimCSE on STS (language), and GraphCL and MVGRL on graph datasets.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: B3 Comparison With Baselines On Graphsmentioning

confidence: 99%

See 1 more Smart Citation

BatchSampler: Sampling Mini-Batches for Contrastive Learning in Vision, Language, and Graphs

Yang

Ming

Dong

et al. 2023

Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining

View full text Add to dashboard Cite

show abstract

“…In graphbased ranking methods, Huang et al [23] integrated attention mechanisms into a tag-based graph neural network, extracting features from the user-item-tag graph structure and utilising attention strategies to discern the importance of different connecting nodes. Xu et al [41] proposed a graph network structure that employs contrastive learning. They utilised the contrastive learning paradigm in the user-item-tag interaction graph to generate reliable and accurate features.…”

Section: Tag Recommendation Methodsmentioning

confidence: 99%

Deep feature fusion‐based stacked denoising autoencoder for tag recommendation systems

Fei,

Wang,

Liu

et al. 2023

IET Cyber-Syst and Robotics

View full text Add to dashboard Cite

With the rapid development of artificial intelligence technology, commercial robots have gradually entered our daily lives. In order to promote product dissemination, shopping guide robots are a new service options of commerce platforms that use tag recommendation systems to identify users' intentions. A large number of applications combine user historical tagging information with the multi‐round dialogue ability of shopping guide robots to help users efficiently search for and retrieve products of interest. Recently, tensor decomposition methods have become a common approach for modelling entity interaction relationships in tag recommendation systems. However, due to the sparsity of data, these methods only consider low‐order information of entities, making it difficult to capture the higher‐order collaborative signals among entities. Recommendation methods by autoencoders can effectively extract abstract feature representations while they only focus on the two‐dimensional relationship between users and items, ignoring the interaction relationship among users, items and tags in real complex recommendation scenarios. The authors focus on modelling the similarity relationship among entities and propose a method called deep feature fusion tag (DFFT) based on the deep feature fusion of stacked denoising autoencoders. This method can extract high‐order information with different embedding dimensions and fuse them in a unified framework. To extract robust feature representations, the authors inject random noise (mask‐out/drop‐out noise) into the tag information corresponding to users and items to generate corrupted input data, and then utilise autoencoders to encode the interaction relationship among entities. To further obtain the interaction relationship with different dimensions, different encoding layers are stacked and combined to produce a better expanded model which can reinforce each other. Finally, a decoding component is used to reconstruct the original input data. According to the experimental results on two common datasets, the proposed DFFT method outperforms other baselines in terms of the F1@N, NDCG@N and Recall@N evaluation metrics.

show abstract

“…Image sentiment analysis can be categorized into two approaches: visual features and semantic features ( Xu et al, 2023 ). Zhu et al (2022) defined 102 mid-level semantic representations for image sentiment analysis, resulting in better sentiment prediction results than visual low-level features alone.…”

Section: Related Workmentioning

confidence: 99%

Art appreciation model design based on improved PageRank and ECA-ResNeXt50 algorithm

Yang,

Chen

2023

PeerJ Computer Science

View full text Add to dashboard Cite

Image sentiment analysis technology can predict, measure and understand the emotional experience of human beings through images. Aiming at the problem of extracting emotional characteristics in art appreciation, this article puts forward an innovative method. Firstly, the PageRank algorithm is enhanced using tweet content similarity and time factors; secondly, the SE-ResNet network design is used to integrate Efficient Channel Attention (ECA) with the residual network structure, and ResNeXt50 is optimized to enhance the extraction of image sentiment features. Finally, the weight coefficients of overall emotions are dynamically adjusted to select a specific emotion incorporation strategy, resulting in effective bimodal fusion. The proposed model demonstrates exceptional performance in predicting sentiment labels, with maximum classification accuracy reaching 88.20%. The accuracy improvement of 21.34% compared to the traditional deep convolutional neural networks (DCNN) model attests to the effectiveness of this study. This research enriches images and texts’ emotion feature extraction capabilities and improves the accuracy of emotion fusion classification.

show abstract

A fairness-aware graph contrastive learning recommender framework for social tagging systems

Cited by 18 publications

References 34 publications

BatchSampler: Sampling Mini-Batches for Contrastive Learning in Vision, Language, and Graphs

BatchSampler: Sampling Mini-Batches for Contrastive Learning in Vision, Language, and Graphs

Deep feature fusion‐based stacked denoising autoencoder for tag recommendation systems

Art appreciation model design based on improved PageRank and ECA-ResNeXt50 algorithm

Contact Info

Product

Resources

About