Generative Adversarial Regularized Mutual Information Policy Gradient Framework for Automatic Diagnosis

@inproceedings{Xia2020GenerativeAR,
  title={Generative Adversarial Regularized Mutual Information Policy Gradient Framework for Automatic Diagnosis},
  author={Yuan Xia and Jingbo Zhou and Zhenhui Shi and Chao Lu and Haifeng Huang},
  booktitle={AAAI},
  year={2020}
}
Automatic diagnosis systems have attracted increasing attention in recent years. The reinforcement learning (RL) is an attractive technique for building an automatic diagnosis system due to its advantages for handling sequential decision making problem. However, the RL method still cannot achieve good enough prediction accuracy. In this paper, we propose a Generative Adversarial regularized Mutual information Policy gradient framework (GAMP) for automatic diagnosis which aims to make a… Expand

Figures, Tables, and Topics from this paper

FIT: a Fast and Accurate Framework for Solving Medical Inquiring and Diagnosing Tasks
TLDR
FIT improves over previous information-based approaches by using a multimodal variational autoencoder model and a two-step sampling strategy for disease prediction and is shown to be a competitive alternative in real-world settings. Expand
Semi-Supervised Variational Reasoning for Medical Dialogue Generation
TLDR
This work proposes an end-to-end variational reasoning approach to medical dialogue generation that outperforms state-of-the-art baselines in terms of objective and subjective evaluation metrics and uses an efficient stochastic gradient variational Bayes estimator to optimize the derived evidence lower bound. Expand
A Weighted Heterogeneous Graph Based Dialogue System
Knowledge based dialogue systems have attracted increasing research interest in diverse applications. However, for disease diagnosis, the widely used knowledge graph is hard to represent theExpand
On the Generation of Medical Dialogues for COVID19
TLDR
This work aims to develop a medical dialogue system that can provide COVID19-related consultations and takes the pretrained models of Transformer, GPT, and BERT-GPT on dialog datasets and other large-scale texts, then finetune them on CovidDialog datasets. Expand
On the Generation of Medical Dialogs for COVID-19
TLDR
A multi-task learning approach is developed, which regularizes the data-deficient dialog generation task with a masked token prediction task, and shows that the generated responses are promising in being doctorlike, relevant to conversation history, clinically informative and correct. Expand
MedDialog: Large-scale Medical Dialogue Datasets
TLDR
It is shown that via transfer learning which finetunes the models pretrained on MedDialog, the performance on medical dialogue generation tasks with small datasets can be greatly improved, as shown in human evaluation and automatic evaluation. Expand
MedDialog: A Large-scale Medical Dialogue Dataset
TLDR
It is shown that via transfer learning which finetunes the models pretrained on MedDialog, the performance on medical dialogue generation tasks with small datasets can be greatly improved, as shown in human evaluation and automatic evaluation. Expand
Description Generation for Points of Interest
TLDR
An extensive experimental evaluation on a large-scale real-world dataset is conducted on a novel model, named as Multi Mode Description Generator (MMDG), to automatically generate description based on POI reviews and other features, to demonstrate its effectiveness and superiority over state-of-the-art baselines in terms of various metrics. Expand
M^2-MedDialog: A Dataset and Benchmarks for Multi-domain Multi-service Medical Dialogues
  • Guojun Yan, Jiahuan Pei, Pengjie Ren, Zhumin Chen, Zhaochun Ren, Huasheng Liang
  • Computer Science
  • ArXiv
  • 2021
Medical dialogue systems (MDSs) aim to assist doctors and patients with a range of professional medical services, i.e., diagnosis, consultation, and treatment. However, one-stop MDS is stillExpand
Medical Entity Relation Verification with Large-scale Machine Reading Comprehension
  • Yuan Xia, Chunyu Wang, +4 authors Hui Xiong
  • Computer Science
  • KDD
  • 2021
Medical entity relation verification is a crucial step to build a practical and enterprise medical knowledge graph (MKG) because high-precision medical entity relation is a key requirement for manyExpand
...
1
2
...

References

SHOWING 1-10 OF 29 REFERENCES
SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient
TLDR
Modeling the data generator as a stochastic policy in reinforcement learning (RL), SeqGAN bypasses the generator differentiation problem by directly performing gradient policy update. Expand
Generative Adversarial Nets
We propose a new framework for estimating generative models via an adversarial process, in which we simultaneously train two models: a generative model G that captures the data distribution, and aExpand
InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets
TLDR
Experiments show that InfoGAN learns interpretable representations that are competitive with representations learned by existing fully supervised methods. Expand
Conditional Generative Adversarial Nets
TLDR
The conditional version of generative adversarial nets is introduced, which can be constructed by simply feeding the data, y, to the generator and discriminator, and it is shown that this model can generate MNIST digits conditioned on class labels. Expand
Adversarial Learning for Neural Dialogue Generation
TLDR
This work applies adversarial training to open-domain dialogue generation, training a system to produce sequences that are indistinguishable from human-generated dialogue utterances, and investigates models for adversarial evaluation that uses success in fooling an adversary as a dialogue evaluation metric, while avoiding a number of potential pitfalls. Expand
REFUEL: Exploring Sparse Features in Deep Reinforcement Learning for Fast Disease Diagnosis
TLDR
REFUEL, a reinforcement learning method with two techniques: reward shaping and feature rebuilding, is proposed to improve the performance of online symptom checking for disease diagnosis. Expand
Adam: A Method for Stochastic Optimization
TLDR
This work introduces Adam, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments, and provides a regret bound on the convergence rate that is comparable to the best known results under the online convex optimization framework. Expand
Reinforcement Learning in Healthcare: A Survey
TLDR
This survey discusses the broad applications of RL techniques in healthcare domains to provide the research community with systematic understanding of theoretical foundations, enabling methods and techniques, existing challenges, and new insights of this emerging paradigm. Expand
Mastering the game of Go with deep neural networks and tree search
TLDR
Using this search algorithm, the program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0.5, the first time that a computer program has defeated a human professional player in the full-sized game of Go. Expand
Playing Atari with Deep Reinforcement Learning
TLDR
This work presents the first deep learning model to successfully learn control policies directly from high-dimensional sensory input using reinforcement learning, which outperforms all previous approaches on six of the games and surpasses a human expert on three of them. Expand
...
1
2
3
...