VIP内容

在当今的信息和计算社会中,复杂系统常常被建模为与异质结构关系、非结构化属性/内容、时间上下文或它们的组合相关联的多模态网络。多模态网络中丰富的信息要求在进行特征工程时既要有一个领域的理解,又要有一个大的探索性搜索空间,以建立针对不同目的的定制化智能解决方案。因此,在多模态网络中,通过表示学习自动发现特征已成为许多应用的必要。在本教程中,我们系统地回顾了多模态网络表示学习的领域,包括一系列最近的方法和应用。这些方法将分别从无监督、半监督和监督学习的角度进行分类和介绍,并分别给出相应的实际应用。最后,我们总结了本教程并进行了公开讨论。本教程的作者是这一领域活跃且富有成效的研究人员。

https://chuxuzhang.github.io/KDD20_Tutorial.html

  • Part 1: Introduction and Overview 导论与概述 (Nitesh Chawla) (1:00-1:10pm) [slide] [video]
  • Part 2: Supervised Methods and Applications 监督方法与应用 2-1: User and behavior modeling (Meng Jiang) (1:10-1- :50pm) [slide] [video] 2-2: Cybersecurity and health intelligence (Yanfang Ye) (1:50-2:20pm) [slide] [video] 2-3: Relation learning (Chuxu Zhang) (2:20-2:35pm) [slide] [video] Coffee Break (2:35-3:00pm)
  • Part 3: Semi-supervised Methods and Applications 半监督方法与应用 3-1: Attributed network embedding (Xiangliang Zhang) (3:00-3:25pm) [slide] [video] 3-2: Graph alignment (Xiangliang Zhang) (3:25-3:40pm) [slide] [video]
  • Part 4: Unsupervised Methods and Applications 无监督方法与应用 4-1: Heterogeneous graph representation learning (Chuxu Zhang) (3:40-4:00pm) [slide] [video] 4-2: Graph neural network for dynamic graph and unsupervised anomaly detection (Meng Jiang) (4:00-4:20pm) [slide] [video] Part 5: Conclusions (Chuxu Zhang) (4:20-5:00pm) [slide] [video] 结论
成为VIP会员查看完整内容
0
63

最新内容

Accurate news representation is critical for news recommendation. Most of existing news representation methods learn news representations only from news texts while ignore the visual information in news like images. In fact, users may click news not only because of the interest in news titles but also due to the attraction of news images. Thus, images are useful for representing news and predicting user behaviors. In this paper, we propose a multimodal news recommendation method, which can incorporate both textual and visual information of news to learn multimodal news representations. We first extract region-of-interests (ROIs) from news images via objective detection. Then we use a pre-trained visiolinguistic model to encode both news texts and news image ROIs and model their inherent relatedness using co-attentional Transformers. In addition, we propose a crossmodal candidate-aware attention network to select relevant historical clicked news for accurate user modeling by measuring the crossmodal relatedness between clicked news and candidate news. Experiments validate that incorporating multimodal news information can effectively improve news recommendation.

0
0
下载
预览

最新论文

Accurate news representation is critical for news recommendation. Most of existing news representation methods learn news representations only from news texts while ignore the visual information in news like images. In fact, users may click news not only because of the interest in news titles but also due to the attraction of news images. Thus, images are useful for representing news and predicting user behaviors. In this paper, we propose a multimodal news recommendation method, which can incorporate both textual and visual information of news to learn multimodal news representations. We first extract region-of-interests (ROIs) from news images via objective detection. Then we use a pre-trained visiolinguistic model to encode both news texts and news image ROIs and model their inherent relatedness using co-attentional Transformers. In addition, we propose a crossmodal candidate-aware attention network to select relevant historical clicked news for accurate user modeling by measuring the crossmodal relatedness between clicked news and candidate news. Experiments validate that incorporating multimodal news information can effectively improve news recommendation.

0
0
下载
预览
Top