Conditional Hybrid GAN For Sequence Generation

Abstract

Conditional sequence generation aims to instruct the generation procedure by conditioning the model with additional context information, which is a self-supervised learning issue (a form of unsupervised learning with supervision information from data itself). Unfortunately, the current state-of-the-art generative models have limitations in sequence generation with multiple attributes. In this paper, we propose a novel conditional hybrid GAN (C-Hybrid-GAN) to solve this issue. Discrete sequence with triplet attributes are separately generated when conditioned on the same context. Most importantly, relational reasoning technique is exploited to model not only the dependency inside each sequence of the attribute during the training of the generator but also the consistency among the sequences of attributes during the training of the discriminator. To avoid the non-differentiability problem in GANs encountered during discrete data generation, we exploit the Gumbel-Softmax technique to appr

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyyu2020conditional

Related papers

• Objective-reinforced Generative Adversarial Networks (ORGAN) For Sequence Generation Models (2017)0.00
• Semi-recurrent Cnn-based VAE-GAN For Sequential Data Generation (2018)10.21
• Chunked Autoregressive GAN For Conditional Waveform Synthesis (2021)0.00
• On Enhancing Speech Emotion Recognition Using Generative Adversarial Networks (2018)12.33
• Bandcondinet: Parallel Transformers-based Conditional Popular Music Generation With Multi-view Features (2024)0.00
• C3net: Compound Conditioned Controlnet For Multimodal Content Generation (2023)5.84
• Polyphonic Music Generation With Sequence Generative Adversarial Networks (2017)2.26
• Conditional Wavegan (2018)4.22