Causality-based CTR prediction using graph neural networks

Zhai, Panyu; Yang, Yanwu; Zhang, Chunjie

doi:10.1016/j.ipm.2022.103137

Cited by 20 publications

(2 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Interactions between keywords can be expressed by various graphs in terms of co-occurrence relationships, semantic relationships and performance influences that can be obtained either by analyzing search advertising logs or by extracting the corpus of vocabulary dictionaries/corpus (e.g., thesaurus dictionary, Wikipedia). Graph models such as graph neural networks (GNNs) are capable of dealing with non-Euclidean graph data by representing high-order feature interactions in the graph structure (Zhai et al, 2023). Hence, GNN can be used to model complex interactions and relationships and thus improve the performance of keyword decision models.…”

Section: Deep Learning Technologies For Keyword Decisionsmentioning

confidence: 99%

Keyword decisions in sponsored search advertising: A literature review and research agenda

Yang

Li²

2023

Information Processing & Management

Self Cite

View full text Add to dashboard Cite

Section: Deep Learning Technologies For Keyword Decisionsmentioning

confidence: 99%

Keyword decisions in sponsored search advertising: A literature review and research agenda

Yang

Li²

2023

Information Processing & Management

Self Cite

View full text Add to dashboard Cite

“…This process requires the construction of a causal feature graph in order to understand the causal links and thus obtain the acquisition of higher order feature representations between nodes. In this paper, by extending the Structural Equation Model (SEM) [24,25] to causal learning so as to better understand the causal relationships between variables in order to facilitate the recovery of W ( f ) , a DAG structure, from the sequence X, the calculations are as follows:…”

Section: Causal Feature Graphmentioning

confidence: 99%

Harnessing Causal Structure Alignment for Enhanced Cross-Domain Named Entity Recognition

Liu,

Cao,

Yang

et al. 2023

Electronics

View full text Add to dashboard Cite

Cross-domain named entity recognition (NER) is a crucial task in various practical applications, particularly when faced with the challenge of limited data availability in target domains. Existing methodologies primarily depend on feature representation or model parameter sharing mechanisms to enable the transfer of entity recognition capabilities across domains. However, these approaches often ignore the latent causal relationships inherent in invariant features. To address this limitation, we propose a novel framework, the Causal Structure Alignment-based Cross-Domain Named Entity Recognition (CSA-NER) framework, designed to harness the causally invariant features within causal structures to enhance the cross-domain transfer of entity recognition competence. Initially, CSA-NER constructs a causal feature graph utilizing causal discovery to ascertain causal relationships between entities and contextual features across source and target domains. Subsequently, it performs graph structure alignment to extract causal invariant knowledge across domains via the graph optimal transport (GOT) method. Finally, the acquired causal invariant knowledge is refined and utilized through the integration of Gated Attention Units (GAUs). Comprehensive experiments conducted on five English datasets and a specific CD-NER dataset exhibit a notable improvement in the average performance of the CSA-NER model in comparison to existing cross-domain methods. These findings underscore the significance of unearthing and employing latent causal invariant knowledge to effectively augment the entity recognition capabilities in target domains, thereby contributing a robust methodology to the broader realm of cross-domain natural language processing.

show abstract

EpiRiskNet: incorporating graph structure and static data as prior knowledge for improved time-series forecasting

Shi,

Chen,

et al. 2024

Appl Intell

View full text Add to dashboard Cite

Causality-based CTR prediction using graph neural networks

Cited by 20 publications

References 55 publications

Keyword decisions in sponsored search advertising: A literature review and research agenda

Keyword decisions in sponsored search advertising: A literature review and research agenda

Harnessing Causal Structure Alignment for Enhanced Cross-Domain Named Entity Recognition

EpiRiskNet: incorporating graph structure and static data as prior knowledge for improved time-series forecasting

Contact Info

Product

Resources

About