Learning and Updating Node Embedding on Dynamic Heterogeneous Information Network

Xie, Yuanzhen; Ou, Zijing; Chen, Liang; Liu, Yang; Xu, Kun; Yang, Carl; Zheng, Zibin

doi:10.1145/3437963.3441745

Cited by 23 publications

(6 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Specifically, besides modeling items independently, we also compose consecutive item groups with different lengths as consecutive intent units (CIUs) and then model the transition relationships among these CIUs by a Multi-granularity Intent Heterogeneous Session Graph (MIHSG). In this heterogeneous graph [39], nodes (CIUs) with different numbers of items are categorized into different groups and the transition edges among the same type of nodes capture the spatial continuity of the user-item interactions in the corresponding intent granularity. We also introduce a special type of edge to represent the transition between high order intent units and the single items, which explicitly encode the intent evolution between coarse and fine-grained granularities.…”

Section: Introductionmentioning

confidence: 99%

Learning Multi-granularity Consecutive User Intent Unit for Session-based Recommendation

Guo

Yang

Song

et al. 2022

Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

Session-based recommendation aims to predict a user's next action based on previous actions in the current session. The major challenge is to capture authentic and complete user preferences in the entire session. Recent work utilizes graph structure to represent the entire session and adopts Graph Neural Network (GNN) to encode session information. This modeling choice has been proved to be effective and achieved remarkable results. However, most of the existing studies only consider each item within the session independently and do not capture session semantics from a high-level perspective. Such limitation often leads to severe information loss and increases the difficulty of capturing long-range dependencies within a session.Intuitively, compared with individual items, a session snippet, i.e., a group of locally consecutive items, is able to provide supplemental user intents which are hardly captured by existing methods. In this work, we propose to learn multi-granularity consecutive user intent unit to improve the recommendation performance. Specifically, we creatively propose Multi-granularity Intent Heterogeneous Session Graph (MIHSG) which captures the interactions between different granularity intent units and relieves the burden of long-dependency. Moreover, we propose the Intent Fusion Ranking (IFR) module to compose the recommendation results from various granularity user intents. Compared with current methods that only leverage intents from individual items, IFR benefits from different granularity user intents to generate more accurate and comprehensive session representation, thus eventually boosting recommendation performance. We conduct extensive experiments on five session-based recommendation datasets and the results demonstrate the effectiveness of our method. Compared to current state-of-the-art methods, we achieve as large as 10.21% gain on HR@20 and 15.53%

show abstract

Section: Introductionmentioning

confidence: 99%

Learning Multi-granularity Consecutive User Intent Unit for Session-based Recommendation

Guo

Yang

Song

et al. 2022

Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining

View full text Add to dashboard Cite

show abstract

“…More recently, Ji et al [20] introduce a Hawkes-process-based method to model the formation process of heterogeneous events adequately and use the importance sampling strategy to capture representative events for influence propagation. Xie et al [21] propose the DyHINE method, comprising a temporal dynamic embedding module and an online updating module, which can deploy real-time updated embedding when the network evolves.…”

Section: Introductionmentioning

confidence: 99%

“…Xie et al. [ 21 ] propose the DyHINE method, comprising a temporal dynamic embedding module and an online updating module, which can deploy real-time updated embedding when the network evolves.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Heterogeneous User Generated Contents-Driven Relation Assessment via Graph Representation Learning

Huang

Chen

et al. 2022

Sensors

View full text Add to dashboard Cite

Cross-domain decision-making systems are suffering a huge challenge with the rapidly emerging uneven quality of user-generated data, which poses a heavy responsibility to online platforms. Current content analysis methods primarily concentrate on non-textual contents, such as images and videos themselves, while ignoring the interrelationship between each user post’s contents. In this paper, we propose a novel framework named community-aware dynamic heterogeneous graph embedding (CDHNE) for relationship assessment, capable of mining heterogeneous information, latent community structure and dynamic characteristics from user-generated contents (UGC), which aims to solve complex non-euclidean structured problems. Specifically, we introduce the Markov-chain-based metapath to extract heterogeneous contents and semantics in UGC. A edge-centric attention mechanism is elaborated for localized feature aggregation. Thereafter, we obtain the node representations from micro perspective and apply it to the discovery of global structure by a clustering technique. In order to uncover the temporal evolutionary patterns, we devise an encoder–decoder structure, containing multiple recurrent memory units, which helps to capture the dynamics for relation assessment efficiently and effectively. Extensive experiments on four real-world datasets are conducted in this work, which demonstrate that CDHNE outperforms other baselines due to the comprehensive node representation, while also exhibiting the superiority of CDHNE in relation assessment. The proposed model is presented as a method of breaking down the barriers between traditional UGC analysis and their abstract network analysis.

show abstract

“…In contrast, the graph structures remains unchanged for epidemiological networks, but the node features inevitably change with increased/decreased patient numbers. It is worth noting that dynamic heterogeneous graphs [14,15,16,17] can be treated as an instance of HTGs, where the dynamic nature comes from the evolving graph structures.…”

Section: Introductionmentioning

confidence: 99%

“…Spatial-temporal graphs [11,18,6,5] and dynamic graphs with homogeneous structures [12,30,13] have been widely studied in the literature. To further consider the graph heterogeneity, learning on dynamic heterogeneous graphs has drawn increasing attention, including dynamic heterogeneous graph embedding models [31,32,17,14] that solely consider graph structures and dynamic heterogeneous GNNs [15,20,33,34] that take both graph structure and node features into consideration. DyHATR [15] first introduces node-level and edge-level attentions to learn heterogeneous information and then applies RNNs with temporal attention to capture temporal dependencies.…”

Section: Introductionmentioning

confidence: 99%

Heterogeneous Temporal Graph Neural Network

Yu¹,

Ju²,

Zhang³

et al. 2021

Preprint

View full text Add to dashboard Cite

Graph neural networks (GNNs) have been broadly studied on dynamic graphs for their representation learning, majority of which focus on graphs with homogeneous structures in the spatial domain. However, many real-world graphs -i.e., heterogeneous temporal graphs (HTGs) -evolve dynamically in the context of heterogeneous graph structures. The dynamics associated with heterogeneity have posed new challenges for HTG representation learning. To solve this problem, in this paper, we propose heterogeneous temporal graph neural network (HTGNN) to integrate both spatial and temporal dependencies while preserving the heterogeneity to learn node representations over HTGs. Specifically, in each layer of HTGNN, we propose a hierarchical aggregation mechanism, including intra-relation, inter-relation, and across-time aggregations, to jointly model heterogeneous spatial dependencies and temporal dimensions. To retain the heterogeneity, intra-relation aggregation is first performed over each slice of HTG to attentively aggregate information of neighbors with the same type of relation, and then intrarelation aggregation is exploited to gather information over different types of relations; to handle temporal dependencies, across-time aggregation is conducted to exchange information across different graph slices over the HTG. The proposed HTGNN is a holistic framework tailored heterogeneity with evolution in time and space for HTG representation learning. Extensive experiments are conducted on the HTGs built from different real-world datasets and promising results demonstrate the outstanding performance of HT-GNN by comparison with state-of-the-art baselines. Our built HTGs and code have been made publicly accessible at: https://github.com/YesLab-Code/HTGNN.

show abstract

Learning and Updating Node Embedding on Dynamic Heterogeneous Information Network

Cited by 23 publications

References 24 publications

Learning Multi-granularity Consecutive User Intent Unit for Session-based Recommendation

Learning Multi-granularity Consecutive User Intent Unit for Session-based Recommendation

Dynamic Heterogeneous User Generated Contents-Driven Relation Assessment via Graph Representation Learning

Heterogeneous Temporal Graph Neural Network

Contact Info

Product

Resources

About