Learning the Implicit Semantic Representation on Graph-Structured Data

Wu, Likang; Li, Zhi; Zhao, Hongke; Liu, Qi; Wang, Jun; Zhang, Mengdi; Chen, Enhong

doi:10.1007/978-3-030-73194-6_1

Cited by 10 publications

(3 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To equip LLM with the ability to comprehend interactive relationships in graph data, we propose a meta-path-based prompt constructor to obtain prompt inputs that represent local subgraphs. Before delving into the details of our approach, it is necessary to provide a formal introduction to heterogeneous graph and meta-path (Wu et al 2021b). Definition 1.…”

Section: Behavior Meta-path Prompt Generationmentioning

confidence: 99%

Exploring Large Language Model for Graph Data Understanding in Online Job Recommendations

Wu,

Qiu,

Zheng

et al. 2024

AAAI

View full text Add to dashboard Cite

Large Language Models (LLMs) have revolutionized natural language processing tasks, demonstrating their exceptional capabilities in various domains. However, their potential for graph semantic mining in job recommendations remains largely unexplored. This paper focuses on unveiling the capability of large language models in understanding behavior graphs and leveraging this understanding to enhance recommendations in online recruitment, including promoting out-of-distribution (OOD) applications. We present a novel framework that harnesses the rich contextual information and semantic representations provided by large language models to analyze behavior graphs and uncover underlying patterns and relationships. Specifically, we propose a meta-path prompt constructor that aids LLM recommender in grasping the semantics of behavior graphs for the first time and design a corresponding path augmentation module to alleviate the prompt bias introduced by path-based sequence input. By facilitating this capability, our framework enables personalized and accurate job recommendations for individual users. We evaluate the effectiveness of our approach on comprehensive real-world datasets and demonstrate its ability to improve the relevance and quality of recommended results. This research not only sheds light on the untapped potential of large language models but also provides valuable insights for developing advanced recommendation systems in the recruitment market. The findings contribute to the growing field of natural language processing and offer practical implications for enhancing job search experiences.

show abstract

Section: Behavior Meta-path Prompt Generationmentioning

confidence: 99%

Exploring Large Language Model for Graph Data Understanding in Online Job Recommendations

Wu,

Qiu,

Zheng

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…ConvGNNs can be categorized into spectral-based ConvGNNs and spatial-based ConvGNNs. Spectral-based approaches define graph convolution based on graph signal processing and spatial-based ConvGNNs including DCNN [25], Graph-SAGE [26], FastGCN [27], GIN [28], and SemanticGCN [29] inherit ideas from RecGNNs by information propagation. Recently, scholars have paid attention to compute mutual information between high dimensional input/output pairs of deep neural networks in diverse domains such as images and speech.…”

Section: B Graph Neural Networkmentioning

confidence: 99%

Deep Graph Learning for Anomalous Citation Detection

Liu

Xia

et al. 2022

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

Anomaly detection is one of the most active research areas in various critical domains, such as healthcare, fintech, and public security. However, little attention has been paid to scholarly data, i.e., anomaly detection in a citation network. Citation is considered as one of the most crucial metrics to evaluate the impact of scientific research, which may be gamed in multiple ways. Therefore, anomaly detection in citation networks is of significant importance to identify manipulation and inflation of citations. To address this open issue, we propose a novel deep graph learning model, namely GLAD (Graph Learning for Anomaly Detection), to identify anomalies in citation networks. GLAD incorporates text semantic mining to network representation learning by adding both node attributes and link attributes via graph neural networks. It exploits not only the relevance of citation contents but also hidden relationships between papers. Within the GLAD framework, we propose an algorithm called CPU (Citation PUrpose) to discover the purpose of citation based on citation texts. The performance of GLAD is validated through a simulated anomalous citation dataset. Experimental results demonstrate the effectiveness of GLAD on the anomalous citation detection task.

show abstract

“…And the user's state activation affected by social influence cannot be simulated by them, which is crucial to judge a user's reposting probability for a message. Recently, with the booming of graph neural networks for network embedding [7,9,16,18,22], such network-aware predictions via representation-based models can effectively model the interpersonal influence [2,13] between nodes (users) and capture the network structure [3,11,20,21] at the same time, which overcome the technical obstacle of heuristic features and gradually make more and more breakthroughs in the area of information cascade prediction.…”

Section: Introductionmentioning

confidence: 99%

Preference Enhanced Social Influence Modeling for Network-Aware Cascade Prediction

Wu¹,

Wang²,

Chen³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Network-aware cascade size prediction aims to predict the final reposted number of user-generated information via modeling the propagation process in social networks. Estimating the user's reposting probability by social influence, namely state activation plays an important role in the information diffusion process. Therefore, Graph Neural Networks (GNN), which can simulate the information interaction between nodes, has been proved as an effective scheme to handle this prediction task. However, existing studies including GNN-based models usually neglect a vital factor of user's preference which influences the state activation deeply. To that end, we propose a novel framework to promote cascade size prediction by enhancing the user preference modeling according to three stages, i.e., preference topics generation, preference shift modeling, and social influence activation. Our end-to-end method makes the user activating process of information diffusion more adaptive and accurate. Extensive experiments on two large-scale real-world datasets have clearly demonstrated the effectiveness of our proposed model compared to state-of-the-art baselines.

show abstract

Learning the Implicit Semantic Representation on Graph-Structured Data

Cited by 10 publications

References 19 publications

Exploring Large Language Model for Graph Data Understanding in Online Job Recommendations

Exploring Large Language Model for Graph Data Understanding in Online Job Recommendations

Deep Graph Learning for Anomalous Citation Detection

Preference Enhanced Social Influence Modeling for Network-Aware Cascade Prediction

Contact Info

Product

Resources

About