paper-with-me

Papers

Adversarial Mutual Information for Text Generation

2020-06-30 · ICML 2020 1 · Boyuan Pan, Yazheng Yang, Kaizhao Liang, Bhavya Kailkhura, Zhongming Jin, Xian-Sheng Hua, Deng Cai, Bo Li

Recent advances in maximizing mutual information (MI) between the source and target have demonstrated its effectiveness in text generation. However, previous works paid little attention to modeling the backward network of MI (i.e., dependency from the target to the source), which is crucial to the tightness of the variational information maximization lower bound. In this paper, we propose Adversarial Mutual Information (AMI): a text generation framework which is formed as a novel saddle point (min-max) optimization aiming to identify joint interactions between the source and target. Within this framework, the forward and backward networks are able to iteratively promote or demote each other's generated instances by comparing the real and synthetic data distributions. We also develop a latent noise sampling strategy that leverages random variations at the high-level semantic space to enhance the long term dependency in the generation process. Extensive experiments based on different text generation tasks demonstrate that the proposed AMI framework can significantly outperform several strong baselines, and we also show that AMI has potential to lead to a tighter lower bound of maximum mutual information for the variational information maximization problem.

📄 PDF Abstract BibTeX arXiv:2007.00067

Code (1)

ZJULearning/AMI 공식 구현 pytorch

Tasks

Text Generation

Similar Papers 제목 키워드 기반

On The Utility of Conditional Generation Based Mutual Information for Characterizing Adversarial Subspaces

2018-09-24 · Chia-Yi Hsu, Pei-Hsuan Lu, Pin-Yu Chen, Chia-Mu Yu

Recent studies have found that deep learning systems are vulnerable to adversarial examples; e.g., visually unrecognizable adversarial images can easily be crafted to result in misclassification. The robustness of neural…

Exploring Adversarial Examples and Adversarial Robustness of Convolutional Neural Networks by Mutual Information

2022-07-12 · Jiebao Zhang, Wenhua Qian, Rencan Nie, Jinde Cao 외

A counter-intuitive property of convolutional neural networks (CNNs) is their inherent susceptibility to adversarial examples, which severely hinders the application of CNNs in security-critical fields. Adversarial examp…

Adversarial Robustness

Mutual Information Maximizing Quantum Generative Adversarial Network and Its Applications in Finance

2023-09-04 · Mingyu Lee, Myeongjin Shin, Junseo Lee, Kabgyun Jeong

One of the most promising applications in the era of NISQ (Noisy Intermediate-Scale Quantum) computing is quantum machine learning. Quantum machine learning offers significant quantum advantages over classical machine le…

Generative Adversarial NetworkImage GenerationQuantum Machine Learning

Disentangled Text Representation Learning with Information-Theoretic Perspective for Adversarial Robustness

2022-10-26 · Jiahao Zhao, Wenji Mao

Adversarial vulnerability remains a major obstacle to constructing reliable NLP systems. When imperceptible perturbations are added to raw input text, the performance of a deep learning model may drop dramatically under …

Adversarial RobustnessRepresentation Learningtext-classificationText Classification

Learning to Disentangle Textual Representations and Attributes via Mutual Information

2021-01-01 · Pierre Colombo, Chloé Clavel, Pablo Piantanida

Learning disentangled representations of textual data is essential for many natural language tasks such as fair classification (\textit{e.g.} building classifiers whose decisions cannot disproportionately hurt or benefi…

AttributeDisentanglementSentenceStyle Transfer