Pinned Repositories
CANM
This code provide the CANM algorithim for causal discovery. Please cite "Ruichu Cai, Jie Qiao, Kun Zhang, Zhenjie Zhang, Zhifeng Hao. Causal Discovery with Cascade Nonlinear Additive Noise Models. IJCAI 2019."
Causal-aware_LLMs
CDMIR
DSAN
DSR
The implement of "Learning Disentangled Semantic Representation for Domain Adaptation" (IJCAI 2019)
LSTD
SADGA
The PyTorch implementation of paper SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL. (NeurIPS 2021)
SASA
SASA-pytorch
SELF
Provides the SELF criteria to learn causal structure. Please cite "Ruichu Cai, Jie Qiao, Zhenjie Zhang, Zhifeng Hao. SELF: Structural Equational Embedded Likelihood Framework for Causal Discovery. AAAI,2018."
DMIRLAB's Repositories
DMIRLAB-Group/SASA
DMIRLAB-Group/SADGA
The PyTorch implementation of paper SADGA: Structure-Aware Dual Graph Aggregation Network for Text-to-SQL. (NeurIPS 2021)
DMIRLAB-Group/SASA-pytorch
DMIRLAB-Group/DSAN
DMIRLAB-Group/DSR
The implement of "Learning Disentangled Semantic Representation for Domain Adaptation" (IJCAI 2019)
DMIRLAB-Group/CANM
This code provide the CANM algorithim for causal discovery. Please cite "Ruichu Cai, Jie Qiao, Kun Zhang, Zhenjie Zhang, Zhifeng Hao. Causal Discovery with Cascade Nonlinear Additive Noise Models. IJCAI 2019."
DMIRLAB-Group/SELF
Provides the SELF criteria to learn causal structure. Please cite "Ruichu Cai, Jie Qiao, Zhenjie Zhang, Zhifeng Hao. SELF: Structural Equational Embedded Likelihood Framework for Causal Discovery. AAAI,2018."
DMIRLAB-Group/GCA
DMIRLAB-Group/TEA
DMIRLAB-Group/REST
DMIRLAB-Group/SSD
DMIRLAB-Group/CCSL
DMIRLAB-Group/DSSL
User activities in real systems are usually time-sensitive. But most of the existing sequential models in recommender systems neglect the time-related signals. In this paper, we find that users' temporal behaviours tend to be driven by their regularly-changing states, which provides a new perspective on learning users' dynamic preference. However, since the individual state is usually latent, the event space is high dimensional, and meanwhile temporal dependency of states is personalized and complex, it is challenging to represent, model and learn the time-evolving patterns of user's state. Focusing on these challenges, we propose a Deep Structured State Learning (DSSL) framework which is able to learn the representation of temporal states and the complex state dependency for time-sensitive recommendation. Extensive experiments demonstrate that DSSL achieves competitive results on four real-world recommendation datasets. Furthermore, experiments also show some interesting rules for designing the state dependency network.
DMIRLAB-Group/Dassl.pytorch
A PyTorch toolbox for domain adaptation and semi-supervised learning.
DMIRLAB-Group/tensorflow-vs-pytorch
Guide for both TensorFlow and PyTorch in comparative way
DMIRLAB-Group/FOM
DMIRLAB-Group/SLMGAE
DMIRLAB-Group/Shared_SSM
Shared State Space Model