AdaVAE: Exploring Adaptive GPT-2s in Variational Auto-Encoders for Language Modeling
Variational Auto-Encoder (VAE) has become the de-facto learning paradigm in achieving representation learning and generation for natural language at the same time. Nevertheless, existing VAE-based language models either employ elementary RNNs, which is not powerful to handle complex works in the multi-task situation, or fine-tunes two pre-trained language models (PLMs) for any downstream task, which is a huge drain on resources. In this paper, we propose the first VAE framework empowered with adaptive GPT-2s (AdaVAE). Different from existing systems, we unify both the encoder\&decoder of the VAE model using GPT-2s with adaptive parameter-efficient components, and further introduce Latent Attention operation to better construct latent space from transformer models. Experiments from multiple dimensions validate that AdaVAE is competent to effectively organize language in three related tasks (language modeling, representation modeling and guided text generation) even with less than $15\%$ activated parameters in training. Our code is available at \url{https://github.com/ImKeTT/AdaVAE}.
Code (1)
Tasks
Conditional Text GenerationDecoderLanguage ModelingLanguage ModellingRepresentation LearningText GenerationSimilar Papers 제목 키워드 기반
AdaVAE: Bayesian Structural Adaptation for Variational Autoencoders
The neural network structures of generative models and their corresponding inference models paired in variational autoencoders (VAEs) play a critical role in the models' generative performance. However, powerful VAE netw…
Implicit supervision for fault detection and segmentation of emerging fault types with Deep Variational Autoencoders
Data-driven fault diagnostics of safety-critical systems often faces the challenge of a complete lack of labeled data associated with faulty system conditions (i.e., fault types) at training time. Since an unknown number…
ClusteringFault DetectionOne-Class ClassificationOne-class classifier+2Learning Correlated Latent Representations with Adaptive Priors
Variational Auto-Encoders (VAEs) have been widely applied for learning compact, low-dimensional latent representations of high-dimensional data. When the correlation structure among data points is available, previous wor…
ClusteringLink PredictionAn Overview on Controllable Text Generation via Variational Auto-Encoders
Recent advances in neural-based generative modeling have reignited the hopes of having computer systems capable of conversing with humans and able to understand natural language. The employment of deep neural architectur…
Text GenerationChallenges for Unsupervised Anomaly Detection in Particle Physics
Anomaly detection relies on designing a score to determine whether a particular event is uncharacteristic of a given background distribution. One way to define a score is to use autoencoders, which rely on the ability to…
Anomaly DetectionUnsupervised Anomaly Detection