• Corpus ID: 237259833

TabGNN: Multiplex Graph Neural Network for Tabular Data Prediction

@article{Guo2021TabGNNMG,
  title={TabGNN: Multiplex Graph Neural Network for Tabular Data Prediction},
  author={Xiawei Guo and Yuhan Quan and Huan Zhao and Quanming Yao and Yong Li and Wei-Wei Tu},
  journal={ArXiv},
  year={2021},
  volume={abs/2108.09127}
}
Tabular data prediction (TDP) is one of the most popular industrial applications, and various methods have been designed to improve the prediction performance. However, existing works mainly focus on feature interactions and ignore sample relations, e.g., users with the same education level might have a similar ability to repay the debt. In this work, by explicitly and systematically modeling sample relations, we propose a novel framework TabGNN based on recently popular graph neural networks… 

Figures and Tables from this paper

Learning Enhanced Representations for Tabular Data via Neighborhood Propagation

TLDR
This paper proposes to 1) construct a hypergraph from relevant data instance retrieval to model the cross-row and cross-column patterns of those instances, and 2) perform message propagation toance the target data instance representation for tabular prediction tasks.

Hopular: Modern Hopfield Networks for Tabular Data

TLDR
Hopular is a novel Deep Learning architecture for mediumand smallsized datasets, where each layer is equipped with continuous modern Hopfield networks, and surpasses Gradient Boosting, Random Forests, SVMs, and in particular several Deep Learning methods on tabular data.

TransTab: Learning Transferable Tabular Transformers Across Tables

TLDR
The goal of TransTab is to convert each sample to a generalizable embedding vector, and then apply stacked transformers for feature encoding, and one methodology insight is combining column description and table cells as the raw input to a gated transformer model.

Multi-view Omics Translation with Multiplex Graph Neural Networks

TLDR
A meso-scale approach to construct multiplex graphs from multi-omics data, which can construct several graphs per omics and cross-omics graphs, and a neural network architecture for omics-to-omics translation from these multipleX graphs, featuring a graph neural network encoder, coupled with an attention layer are proposed.

References

SHOWING 1-10 OF 37 REFERENCES

Multiplex Graph Neural Networks for Multi-behavior Recommendation

TLDR
MGNN tackles the multi-behavior recommendation problem from a novel perspective, i.e., the perspective of link prediction in multiplex networks, by taking advantage of both the multiplex network structure and graph representation learning techniques.

Representation Learning for Attributed Multiplex Heterogeneous Network

TLDR
Results of the offline A/B tests on product recommendation further confirm the effectiveness and efficiency of the framework in practice, and the theoretical analysis of the proposed framework gives its connection with previous works and proving its better expressiveness.

DeepFM: A Factorization-Machine based Neural Network for CTR Prediction

TLDR
This paper shows that it is possible to derive an end-to-end learning model that emphasizes both low- and high-order feature interactions, and combines the power of factorization machines for recommendation and deep learning for feature learning in a new neural network architecture.

Loan Default Analysis with Multiplex Graph Learning

TLDR
A novel attributed multiplex graph based loan default detection approach for effectively integrating multiplex relations in financial scenarios by elaborately design relation-specific receptive layers equipped with adaptive breadth function to incorporate important information derived from local structure in each aspect of AMG.

AutoCross: Automatic Feature Crossing for Tabular Data in Real-World Applications

TLDR
This paper presents AutoCross, an automatic feature crossing tool provided by 4Paradigm to its customers, and shows that AutoCross can significantly enhance the performance of both linear and deep models.

MTBRN: Multiplex Target-Behavior Relation Enhanced Network for Click-Through Rate Prediction

TLDR
A new framework named Multiplex Target-Behavior Relation enhanced Network (MTBRN) is proposed to leverage multiplex relations between user behaviors and target item to enhance CTR prediction.

Deep Interest Network for Click-Through Rate Prediction

TLDR
A novel model: Deep Interest Network (DIN) is proposed which tackles this challenge by designing a local activation unit to adaptively learn the representation of user interests from historical behaviors with respect to a certain ad.

How Powerful are Graph Neural Networks?

TLDR
This work characterize the discriminative power of popular GNN variants, such as Graph Convolutional Networks and GraphSAGE, and show that they cannot learn to distinguish certain simple graph structures, and develops a simple architecture that is provably the most expressive among the class of GNNs.

Multi-dimensional Graph Convolutional Networks

TLDR
This paper proposes a multi-dimensional convolutional neural network model mGCN aiming to capture rich information in learning node-level representations formulti-dimensional graphs and demonstrates the effectiveness of the proposed framework on real-world multi- dimensional graphs.

Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures

TLDR
This work designs a GNN which is both powerful and efficient for molecule structures and builds Multiplex Molecular Graph Neural Network (MXMNet), a molecular mechanics-driven approach which achieves superior results to the existing state-of-the-art models under restricted resources.