The interactive behavior of comments within the user group on microblog website is bidirectional and dynamic, reflecting the level of familiarity among users. Predicting the future comment interaction behavior within ...
详细信息
ISBN:
(纸本)9781665418164
The interactive behavior of comments within the user group on microblog website is bidirectional and dynamic, reflecting the level of familiarity among users. Predicting the future comment interaction behavior within the user group is of great significance for commercial recommendation and crime fighting. Related research groups regard it as a temporal link prediction problem, assume the evolution is smooth or there is no evolution at all. Meanwhile, the feature in those studies is too unitary, leading to low link prediction performance. In this paper, we propose a method called User Group Comment Interaction Behaviour Prediction (UGCIBP), which combines structure extraction layer and evolution extraction layer to do dynamic graph representation learning to acheive the modeling of user group historical comment interaction graphs, and build the features of communication weight, interest similarity, and common degree of activity between users on microblog website. Then, we combine dynamic graph representation learning and the constructed features to do link prediction, finally, the purpose of predicting comment interaction is acheived. Experiments are conducted on the public datasets Enron and Twitter datasets to evaluate the method. The results show that the AUC scores of this method are 4.74% and 9.95% higher than existing methods, respectively, which proves the effectiveness of the UGCIBP method.
Inferring user preferences from users’ historical feedback is a valuable problem in recommender systems. Conventional approaches often rely on the assumption that user preferences in the feedback data are equivalent ...
详细信息
Inferring user preferences from users’ historical feedback is a valuable problem in recommender systems. Conventional approaches often rely on the assumption that user preferences in the feedback data are equivalent to the real user preferences without additional noise, which simplifies the problem modeling. However, there are various confounders during user-item interactions, such as weather and even the recommendation system itself. Therefore, neglecting the influence of confounders will result in inaccurate user preferences and suboptimal performance of the model. Furthermore, the unobservability of confounders poses a challenge in further addressing the problem. Along these lines, we refine the problem and propose a more rational solution to mitigate the influence of unobserved confounders. Specifically, we consider the influence of unobserved confounders, disentangle them from user preferences in the latent space, and employ causal graphs to model their interdependencies without specific labels. By ingeniously combining local and global causal graphs, we capture the user-specific effects of confounders on user preferences. Finally, we propose our model based on Variational Autoencoders, named Causal Structure Aware Variational Autoencoders (CSA-VAE) and theoretically demonstrate the identifiability of the obtained causal graph. We conducted extensive experiments on one synthetic dataset and nine real-world datasets with different scales, including three unbiased datasets and six normal datasets, where the average performance boost against several state-of-the-art baselines achieves up to 9.55%, demonstrating the superiority of our model. Furthermore, users can control their recommendation list by manipulating the learned causal representations of confounders, generating potentially more diverse recommendation results. Our code is available at Code-link.
Massive, multi-dimensional and imbalanced network traffic data has brought new challenges to traditional intrusion detection systems (IDSs). The detection performance of traditional algorithms is closely related to fe...
Massive, multi-dimensional and imbalanced network traffic data has brought new challenges to traditional intrusion detection systems (IDSs). The detection performance of traditional algorithms is closely related to feature extractions, which are not effective in the massive and imbalanced data environments. In this paper, we propose an intrusion detection model based on synthetic minority oversampling technology (SMOTE) and convolutional neural network (CNN) ensemble. It converts original traffic vectors into images, designs a CNN structure, and combines SMOTE and CNN ensemble to solve the problem of imbalanced datasets. Using the standard KDD CUP 99 dataset to evaluate the performance of the proposed model and analysing the contribution of features to model decision-making show that the model's F1 score are better than traditional algorithms in the classes with few samples and the model improves the efficiency of network intrusion detection.
Sentence alignment, as one of the most active and fundamental tasks in the field of natural language processing (NLP), is usually realized in two categories of methods. One is traditional methods which are firstly pro...
详细信息
ISBN:
(纸本)9781450377607
Sentence alignment, as one of the most active and fundamental tasks in the field of natural language processing (NLP), is usually realized in two categories of methods. One is traditional methods which are firstly proposed, the other, which are adopted later, is based on the Neural Network method. Presently, under the limitation that the existing mainstream data corpora are mostly in the form of 1-to-1, the alignment models with relatively good performance mainly apply to the cases of 1-to-1 sentence alignment. However, under the circumstance that a sentence contains too much information, 1-to-N sentence alignment can actually have a better effect on sentence translation tasks, compared with the 1-to-1 form, since it is more flexible and can reduce the complexity of the original sentence. As a result, we attempt to exploit neural networks with relatively good performance in the cases of 1-to-1 to fit in the cases of 1-to-N. In this paper, a novel 1-N Bilingual word Embedding with Sentence Combination CNN Improved Framework (1-NBESCC) is proposed in order to align 1-to-N sentences more precisely. Experiments show that our proposed model performs as good as the traditional methods such as BLEUALIGN in 1-to-1 situation, but much better in 1-to-N situation.
暂无评论