6 papers · 1 filter
Beyond the Black Box: Identifiable Interpretation and Control in Generative Models via Causal Minimality
Lingjing Kong, Shaoan Xie, Guangyi Chen +4
Deep generative models, while revolutionizing fields like image and text generation, largely operate as opaque ``black boxes'', hindering human understanding, control, and alignmen…
Causal Representation Learning from Multimodal Biomedical Observations
Yuewen Sun, Lingjing Kong, Guangyi Chen +10
Prevalent in biomedical applications (e.g., human phenotype research), multimodal datasets can provide valuable insights into the underlying physiological mechanisms. However, curr…
Towards Understanding Extrapolation: a Causal Lens
Lingjing Kong, Guangyi Chen, Petar Stojanov +3
Canonical work handling distribution shifts typically necessitates an entire target distribution that lands inside the training distribution. However, practical scenarios often inv…
Learning Discrete Concepts in Latent Hierarchical Models
Lingjing Kong, Guangyi Chen, Biwei Huang +3
Learning concepts from natural high-dimensional data (e.g., images) holds potential in building human-aligned and interpretable machine learning models. Despite its encouraging pro…
Reducing Hyperparameter Tuning Costs in ML, Vision and Language Model Training Pipelines via Memoization-Awareness
Abdelmajid Essofi, Ridwan Salahuddeen, Munachiso Nwadike +5
The training or fine-tuning of machine learning, vision, and language models is often implemented as a pipeline: a sequence of stages encompassing data preparation, model training…
Temporally Disentangled Representation Learning under Unknown Nonstationarity
Xiangchen Song, Weiran Yao, Yewen Fan +5
In unsupervised causal representation learning for sequential data with time-delayed latent causal influences, strong identifiability results for the disentanglement of causally-re…