Probabilistic Discriminative Learning with Layered Graphical Models
This work addresses the challenge of making probabilistic graphical models effective for discriminative tasks like image classification, offering a transparent alternative to neural networks, though it is incremental in adapting existing graphical model concepts.
The paper tackled the problem of applying probabilistic graphical models to discriminative learning by proposing layered graphical models (LGMs) with deep hierarchical structures and convolutional connections, achieving competitive results on MNIST and FashionMNIST datasets comparable to neural networks of similar architectures.
Probabilistic graphical models are traditionally known for their successes in generative modeling. In this work, we advocate layered graphical models (LGMs) for probabilistic discriminative learning. To this end, we design LGMs in close analogy to neural networks (NNs), that is, they have deep hierarchical structures and convolutional or local connections between layers. Equipped with tensorized truncated variational inference, our LGMs can be efficiently trained via backpropagation on mainstream deep learning frameworks such as PyTorch. To deal with continuous valued inputs, we use a simple yet effective soft-clamping strategy for efficient inference. Through extensive experiments on image classification over MNIST and FashionMNIST datasets, we demonstrate that LGMs are capable of achieving competitive results comparable to NNs of similar architectures, while preserving transparent probabilistic modeling.