Eliminating Contextual Prior Bias for Semantic Image Editing via Dual-Cycle Diffusion

1 code implementation • 5 Feb 2023 • Zuopeng Yang, Tianshu Chu, Xin Lin, Erdun Gao, Daqing Liu, Jie Yang, Chaoyue Wang

The proposed model incorporates a Bias Elimination Cycle that consists of both a forward path and an inverted path, each featuring a Structural Consistency Cycle to ensure the preservation of image content during the editing process.

Text-to-Image Generation

On the Sparse DAG Structure Learning Based on Adaptive Lasso

no code implementations • 7 Sep 2022 • Danru Xu, Erdun Gao, Wei Huang, Menghan Wang, Andy Song, Mingming Gong

Learning the underlying Bayesian Networks (BNs), represented by directed acyclic graphs (DAGs), of the concerned events from purely-observational data is a crucial part of evidential reasoning.

MissDAG: Causal Discovery in the Presence of Missing Data with Continuous Additive Noise Models

1 code implementation • 27 May 2022 • Erdun Gao, Ignavier Ng, Mingming Gong, Li Shen, Wei Huang, Tongliang Liu, Kun Zhang, Howard Bondell

In this paper, we develop a general method, which we call MissDAG, to perform causal discovery from data with incomplete observations.

Causal Discovery Imputation +1

FedDAG: Federated DAG Structure Learning

1 code implementation • 7 Dec 2021 • Erdun Gao, Junjia Chen, Li Shen, Tongliang Liu, Mingming Gong, Howard Bondell

To date, most directed acyclic graphs (DAGs) structure learning approaches require data to be stored in a central server.

Causal Discovery