Deep Extrapolation for Attribute-Enhanced Generation
Attribute extrapolation in sample generation is challenging for deep neural networks operating beyond the training distribution. We formulate a new task for extrapolation in sequence generation, focusing on natural language and proteins, and propose GENhance, a generative framework that enhances attributes through a learned latent space. Trained on movie reviews and a computed protein stability dataset, GENhance can generate strongly-positive text reviews and highly stable protein sequences without being exposed to similar data during training. We release our benchmark tasks and models to contribute to the study of generative modeling extrapolation and data-driven design in biology and chemistry.
Code (1)
Tasks
AttributeSimilar Papers 제목 키워드 기반
Extrapolative Controlled Sequence Generation via Iterative Refinement
We study the problem of extrapolative controlled generation, i.e., generating sequences with attribute values beyond the range seen in training. This task is of significant importance in automated design, especially drug…
AttributeDrug DiscoverySentiment AnalysisMotion Compensated Three-Dimensional Frequency Selective Extrapolation for Improved Error Concealment in Video Communication
During transmission of video data over error-prone channels the risk of getting severe image distortions due to transmission errors is ubiquitous. To deal with image distortions at decoder side, error concealment is appl…
DecoderMotion CompensationMotion EstimationConcept Modulation Models: A Unified Framework for Identifiability and Extrapolation
Reliable generalization in conditional latent variable models requires understanding both identifiability and extrapolation: how observed variation across attributes determines latent structure, and how that structure de…
Representation LearningAn Enhanced Dynamic Ray Tracing Architecture for Channel Prediction Based on Multipath Bidirectional Geometry and Field Extrapolation
With the development of sixth generation (6G) networks toward digitalization and intelligentization of communications, rapid and precise channel prediction is crucial for the network potential release. Interestingly, a d…
PredictionOn Single-environment Extrapolations in Graph Classification and Regression Tasks
Extrapolation in graph classification/regression remains an underexplored area of an otherwise rapidly developing field. Our work contributes to a growing literature by providing the first systematic counterfactual model…
ClassificationcounterfactualGeneral ClassificationGraph Classification+1