DANets: Deep Abstract Networks for Tabular Data Classification and Regression

• URL: http://arxiv.org/abs/2112.02962v1
• Date: Mon, 6 Dec 2021 12:15:28 GMT
• Title: DANets: Deep Abstract Networks for Tabular Data Classification and Regression
• Authors: Jintai Chen, Kuanlun Liao, Yao Wan, Danny Z. Chen, Jian Wu
• Abstract summary: Abstract Layer (AbstLay) learns to explicitly group correlative input features and generate higher-level features for semantics abstraction. Family of Deep Abstract Networks (DANets) for tabular data classification and regression.
• Score: 9.295859461145783
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Tabular data are ubiquitous in real world applications. Although many commonly-used neural components (e.g., convolution) and extensible neural networks (e.g., ResNet) have been developed by the machine learning community, few of them were effective for tabular data and few designs were adequately tailored for tabular data structures. In this paper, we propose a novel and flexible neural component for tabular data, called Abstract Layer (AbstLay), which learns to explicitly group correlative input features and generate higher-level features for semantics abstraction. Also, we design a structure re-parameterization method to compress AbstLay, thus reducing the computational complexity by a clear margin in the reference phase. A special basic block is built using AbstLays, and we construct a family of Deep Abstract Networks (DANets) for tabular data classification and regression by stacking such blocks. In DANets, a special shortcut path is introduced to fetch information from raw tabular features, assisting feature interactions across different levels. Comprehensive experiments on seven real-world tabular datasets show that our AbstLay and DANets are effective for tabular data classification and regression, and the computational complexity is superior to competitive methods. Besides, we evaluate the performance gains of DANet as it goes deep, verifying the extendibility of our method. Our code is available at https://github.com/WhatAShot/DANet.

Related papers

• TabKANet: Tabular Data Modeling with Kolmogorov-Arnold Network and Transformer [12.237450884462888]
  TabKANet is a model for learning from numerical content. It has superior performance compared to Neural Networks (NNs) Our code is publicly available on GitHub.
  arXiv  Detail & Related papers  (2024-09-13T13:14:54Z)
• Deep Feature Embedding for Tabular Data [2.1301560294088318]
  This paper proposes a novel deep embedding framework with leverages lightweight deep neural networks. For numerical features, a two-step feature expansion and deep transformation technique is used to capture copious semantic information. Experiments are conducted on real-world datasets for performance evaluation.
  arXiv  Detail & Related papers  (2024-08-30T10:05:24Z)
• (PASS) Visual Prompt Locates Good Structure Sparsity through a Recurrent HyperNetwork [60.889175951038496]
  Large-scale neural networks have demonstrated remarkable performance in different domains like vision and language processing. One of the key questions of structural pruning is how to estimate the channel significance. We propose a novel algorithmic framework, namely textttPASS. It is a tailored hyper-network to take both visual prompts and network weight statistics as input, and output layer-wise channel sparsity in a recurrent manner.
  arXiv  Detail & Related papers  (2024-07-24T16:47:45Z)
• Data Augmentations in Deep Weight Spaces [89.45272760013928]
  We introduce a novel augmentation scheme based on the Mixup method. We evaluate the performance of these techniques on existing benchmarks as well as new benchmarks we generate.
  arXiv  Detail & Related papers  (2023-11-15T10:43:13Z)
• Graph Neural Network contextual embedding for Deep Learning on Tabular Data [0.45880283710344055]
  Deep Learning (DL) has constituted a major breakthrough for AI in fields related to human skills like natural language processing. This paper presents a novel DL model using Graph Neural Network (GNN) more specifically Interaction Network (IN) Its results outperform those of a recently published survey with DL benchmark based on five public datasets, also achieving competitive results when compared to boosted-tree solutions.
  arXiv  Detail & Related papers  (2023-03-11T17:13:24Z)
• TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second [48.87527918630822]
  We present TabPFN, a trained Transformer that can do supervised classification for small datasets in less than a second. TabPFN performs in-context learning (ICL), it learns to make predictions using sequences of labeled examples. We show that our method clearly outperforms boosted trees and performs on par with complex state-of-the-art AutoML systems with up to 230$times$ speedup.
  arXiv  Detail & Related papers  (2022-07-05T07:17:43Z)
• Transfer Learning with Deep Tabular Models [66.67017691983182]
  We show that upstream data gives tabular neural networks a decisive advantage over GBDT models. We propose a realistic medical diagnosis benchmark for tabular transfer learning. We propose a pseudo-feature method for cases where the upstream and downstream feature sets differ.
  arXiv  Detail & Related papers  (2022-06-30T14:24:32Z)
• A Robust Stacking Framework for Training Deep Graph Models with Multifaceted Node Features [61.92791503017341]
  Graph Neural Networks (GNNs) with numerical node features and graph structure as inputs have demonstrated superior performance on various supervised learning tasks with graph data. The best models for such data types in most standard supervised learning settings with IID (non-graph) data are not easily incorporated into a GNN. Here we propose a robust stacking framework that fuses graph-aware propagation with arbitrary models intended for IID data.
  arXiv  Detail & Related papers  (2022-06-16T22:46:33Z)
• Representation Extraction and Deep Neural Recommendation for Collaborative Filtering [9.367612782346207]
  This paper investigates the usage of novel representation learning algorithms to extract users and items representations from rating matrix. We propose a modular algorithm consisted of two main phases: REpresentation eXtraction and a deep neural NETwork (RexNet) RexNet is not dependent on unstructured auxiliary data such as visual and textual information, instead, it uses only the user-item rate matrix as its input.
  arXiv  Detail & Related papers  (2020-12-09T11:15:23Z)
• EdgeNets:Edge Varying Graph Neural Networks [179.99395949679547]
  This paper puts forth a general framework that unifies state-of-the-art graph neural networks (GNNs) through the concept of EdgeNet. An EdgeNet is a GNN architecture that allows different nodes to use different parameters to weigh the information of different neighbors. This is a general linear and local operation that a node can perform and encompasses under one formulation all existing graph convolutional neural networks (GCNNs) as well as graph attention networks (GATs)
  arXiv  Detail & Related papers  (2020-01-21T15:51:17Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.