Search Results for author:
Found 10 papers, 5 papers with code
Counterfactual Data Augmentation with Contrastive Learning
To address this, we introduce a model-agnostic data augmentation method that imputes the counterfactual outcomes for a selected subset of individuals.
PrACTiS: Perceiver-Attentional Copulas for Time Series
Transformers incorporating copula structures have demonstrated remarkable performance in time series prediction.
Mode-Aware Continual Learning for Conditional Generative Adversarial Networks
To this end, we introduce a new continual learning approach for conditional generative adversarial networks by leveraging a mode-affinity score specifically designed for generative modeling.
Improving Open-Domain Dialogue Evaluation with a Causal Inference Model
We project these features to the dialogue level and train a dialogue-level MLP regression model, a dialogue-level LSTM, and a novel causal inference model called counterfactual-LSTM (CF-LSTM) to predict ratings.
Transfer Learning for Individual Treatment Effect Estimation
To this end, we theoretically assess the feasibility of transferring ITE knowledge and present a practical framework for efficient transfer.
Task Affinity with Maximum Bipartite Matching in Few-Shot Learning
We propose an asymmetric affinity score for representing the complexity of utilizing the knowledge of one task for learning another one.
Fisher Task Distance and Its Application in Neural Architecture Search
Next, we construct an online neural architecture search framework using the Fisher task distance, in which we have access to the past learned tasks.
Improved Automated Machine Learning from Transfer Learning
In this paper, we propose a neural architecture search framework based on a similarity measure between some baseline tasks and a target task.
Task-Aware Neural Architecture Search
The design of handcrafted neural networks requires a lot of time and resources.
Supervised Encoding for Discrete Representation Learning
Classical supervised classification tasks search for a nonlinear mapping that maps each encoded feature directly to a probability mass over the labels.
