Titlebook: Web and Big Data; 7th International Jo Xiangyu Song,Ruyi Feng,Geyong Min Conference proceedings 2024 The Editor(s) (if applicable) and The

Proponent

CONE

,DADR: A Denoising Approach for Dense Retrieval Model Training,ch reduces the effects of noise on model performance by assigning diverse weights to the different samples during the training process. We incorporate the proposed DADR approach with three representative kinds of sampling methods and different loss functions. Experimental results on two publicly ava

笼子

,Multi-pair Contrastive Learning Based on Same-Timestamp Data Augmentation for Sequential Recommendaractions. During the training and testing process, we design three types of samples so as to imitate human learning. Extensive experiments on two benchmark datasets show that our model outperforms state-of-the-art sequential models.

古董

,PaTraS: A Path-Preserving Trajectory Simplification Method for Low-Loss Map Matching,asures the importance of a trajectory point with respect to how it contributes to the map-matching results. Extensive experiments show that, compared with state-of-the-art methods, our proposed solution can better preserve the path generated by trajectory map-matching at the cost of a slightly incre

救护车

,Enhancing Collaborative Features with Knowledge Graph for Recommendation,ant semantic information in KG, we design an attribute aggregation scheme and an inference mechanism for GNN which directly propagates further attributes and inference information to the central node. Extensive experiments conducted on three public datasets demonstrate the superior performance of CK

必死

,DADR: A Denoising Approach for Dense Retrieval Model Training,ch reduces the effects of noise on model performance by assigning diverse weights to the different samples during the training process. We incorporate the proposed DADR approach with three representative kinds of sampling methods and different loss functions. Experimental results on two publicly ava

seroma

,PageCNNs: Convolutional Neural Networks for Multi-label Chinese Webpage Classification with Multi-i Chinese webpages. The proposed PageCNN models are compared with two modified traditional machine learning models, the modified TextCNN model, and three state-of-the-art deep learning based multi-label text classification models. The experimental results demonstrate that the PageCNN models perform b

蚊帐

来这真柔软

易弯曲

,Enhancing Collaborative Features with Knowledge Graph for Recommendation,ant semantic information in KG, we design an attribute aggregation scheme and an inference mechanism for GNN which directly propagates further attributes and inference information to the central node. Extensive experiments conducted on three public datasets demonstrate the superior performance of CK