TextGNN: Improving Text Encoder via Graph Neural Network in Sponsored Search

Zhu, Jason; Cui, Yanling; Liu, Yuming; Sun, Hao; Li, Xue; Pelger, Markus; Yang, Tianqi; Zhang, Liang-Jie; Zhang, Ruofei; Zhao, Huasha

doi:10.1145/3442381.3449842

Cited by 33 publications

(17 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Huang et al build graphs for each text instead of building a large graph containing the whole corpus [17]. GAT and GraphSAGE is adopted by Zhu et al for sponsored search recommendation [18]. These prementioned studies explore ways of representing text information as a graph, while eliminating the graph structure of labels.…”

Section: Gnn For Natural Language Process Tasksmentioning

confidence: 99%

A financial derivatives related multi-label text classification algorithm based on financial knowledge graph

Ma¹,

Lin²,

Miao³

et al. 2023

Third International Conference on Machine Learning and Computer Application (ICMLCA 2022)

View full text Add to dashboard Cite

Section: Gnn For Natural Language Process Tasksmentioning

confidence: 99%

A financial derivatives related multi-label text classification algorithm based on financial knowledge graph

Ma¹,

Lin²,

Miao³

et al. 2023

Third International Conference on Machine Learning and Computer Application (ICMLCA 2022)

View full text Add to dashboard Cite

“…They can be utilized for fine-tuning the models on small datasets, if necessary, to alleviate the overfitting problem and increase the models' generalization capabilities. LSTM [18] BiLSTM [19] LSTM_Attention [20] GRU [21] TextCNN [22] TextRCNN [23] VDCNN [24] RNN-CNN [25] Natural language processing methods Transformer [26] Reformer [27] Performer [28] Linformer [29] RoutingTransformer [30] DNABERT, RNABERT, ProtBERT [2,31] BERT-Base [32] BERT-CNN [33] BERT-DPCNN [34] BERT-RNN ERNIE [35] Graph neural network methods GCN [36] TextGNN [37] GIN [38] GAT [39] GraphSage [40] ChebGCN [41] RECT-L [42] preprint (which was not certified by peer review) is the author/funder. All rights reserved.…”

Section: Deep-learning Prediction Modulementioning

confidence: 99%

DeepBIO is an automated and interpretable deep-learning platform for biological sequence prediction, functional annotation, and visualization analysis

Wang

Jiang

Jin

et al. 2022

Preprint

View full text Add to dashboard Cite

Here, we present DeepBIO, the first-of-its-kind automated and interpretable deep-learning platform for biological sequence functional analysis. DeepBIO is a one-stop-shop web service that enables researchers to develop a new deep-learning architecture to answer any biological question. Specifically, given any biological sequence data, DeepBIO supports a total of 42 state-of-the-art deep-learning algorithms for model training, comparison, optimization, and evaluation in a fully automated pipeline. DeepBIO provides a comprehensive result visualization analysis for the predictive models covering several aspects, such as model interpretability, feature analysis, functional sequential region discovery, etc. Additionally, DeepBIO supports over 20 functional site annotation tasks using deep-learning architectures, with comprehensive interpretations and graphical visualizations to validate the reliability of annotated sites. Empowered by high-performance computers, DeepBIO allows fast prediction with up to million-scale sequence data, demonstrating its usability in real application scenarios. Case study results show that DeepBIO provides an accurate, robust, and interpretable prediction, demonstrating the power of deep learning in biological sequence analysis. Overall, we expect DeepBIO to ensure the reproducibility of deep-learning biological sequence analysis, lessen the programming and hardware burden for biologists, and provide meaningful functional insights at both sequence-level and base-level from biological sequences alone. DeepBIO is publicly available at http://inner.wei-group.net/DeepBIO.

show abstract

“…Graph Neural Networks in Related Areas: A sizeable body of work exists on using graph neural networks such as graph convolutional networks (GCN) for recommendation [22,[55][56][57][58][59][60][61][62][63]. Certain methods e.g., FastGCN [56], KGCL [63], LightGCN [62] learn item embeddings as (functions of) free vectors.…”

Section: Related Workmentioning

confidence: 99%

ECLARE: Extreme Classification with Label Graph Correlations

Mittal

Sachdeva

Agrawal

et al. 2021

Proceedings of the Web Conference 2021

View full text Add to dashboard Cite

Deep extreme classification (XC) seeks to train deep architectures that can tag a data point with its most relevant subset of labels from an extremely large label set. The core utility of XC comes from predicting labels that are rarely seen during training. Such rare labels hold the key to personalized recommendations that can delight and surprise a user. However, the large number of rare labels and small amount of training data per rare label offer significant statistical and computational challenges. State-of-the-art deep XC methods attempt to remedy this by incorporating textual descriptions of labels but do not adequately address the problem. This paper presents ECLARE, a scalable deep learning architecture that incorporates not only label text, but also label correlations, to offer accurate real-time predictions within a few milliseconds. Core contributions of ECLARE include a frugal architecture and scalable techniques to train deep models along with label correlation graphs at the scale of millions of labels. In particular, ECLARE offers predictions that are 2-14% more accurate on both publicly available benchmark datasets as well as proprietary datasets for a related products recommendation task sourced from the Bing search engine. Code for ECLARE is available at https://github.com/Extreme-classification/ECLARE CCS CONCEPTS• Computing methodologies → Machine learning; Supervised learning by classification.

show abstract

TextGNN: Improving Text Encoder via Graph Neural Network in Sponsored Search

Cited by 33 publications

References 16 publications

A financial derivatives related multi-label text classification algorithm based on financial knowledge graph

A financial derivatives related multi-label text classification algorithm based on financial knowledge graph

DeepBIO is an automated and interpretable deep-learning platform for biological sequence prediction, functional annotation, and visualization analysis

ECLARE: Extreme Classification with Label Graph Correlations

Contact Info

Product

Resources

About