516 citations · 545 across the 9 of their papers we have counts for
9 papers
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…
Counterfactual Generation with Identifiability Guarantees
Hanqi Yan, Lingjing Kong, Lin Gui +4
Counterfactual generation lies at the core of various machine learning tasks, including image translation and controllable text generation. This generation process usually requires…
Understanding Masked Autoencoders via Hierarchical Latent Variable Models
Lingjing Kong, Martin Q. Ma, Guangyi Chen +4
Masked autoencoder (MAE), a simple and effective self-supervised learning framework based on the reconstruction of masked image regions, has recently achieved prominent success in…
Identification of Nonlinear Latent Hierarchical Models
Lingjing Kong, Biwei Huang, Feng Xie +3
Identifying latent variables and causal structures from observational data is essential to many real-world applications involving biological data, medical data, and unstructured da…
Partial Identifiability for Domain Adaptation
Lingjing Kong, Shaoan Xie, Weiran Yao +5
Unsupervised domain adaptation is critical to many real-world applications where label information is unavailable in the target domain. In general, without further assumptions, the…
Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems
Fei Mi, Wanhao Zhou, Fengyu Cai +3
As the labeling cost for different modules in task-oriented dialog (ToD) systems is expensive, a major challenge is to train different modules with the least amount of labeled data…
Consensus Control for Decentralized Deep Learning
Lingjing Kong, Tao Lin, Anastasia Koloskova +2
Decentralized training of deep learning models enables on-device learning over networks, as well as efficient scaling to large compute clusters. Experiments in earlier works reveal…
Extrapolation for Large-batch Training in Deep Learning
Tao Lin, Lingjing Kong, Sebastian U. Stich +1
Deep learning networks are typically trained by Stochastic Gradient Descent (SGD) methods that iteratively improve the model parameters by estimating a gradient on a very small fra…
Ensemble Distillation for Robust Model Fusion in Federated Learning
Tao Lin, Lingjing Kong, Sebastian U. Stich +1
Federated Learning (FL) is a machine learning setting where many devices collaboratively train a machine learning model while keeping the training data decentralized. In most of th…