Graphical Models with Attention for Context-Specific Independence and an Application to Perceptual Grouping

by   Guangyao Zhou, et al.

Discrete undirected graphical models, also known as Markov Random Fields (MRFs), can flexibly encode probabilistic interactions of multiple variables, and have enjoyed successful applications to a wide range of problems. However, a well-known yet little studied limitation of discrete MRFs is that they cannot capture context-specific independence (CSI). Existing methods require carefully developed theories and purpose-built inference methods, which limit their applications to only small-scale problems. In this paper, we propose the Markov Attention Model (MAM), a family of discrete MRFs that incorporates an attention mechanism. The attention mechanism allows variables to dynamically attend to some other variables while ignoring the rest, and enables capturing of CSIs in MRFs. A MAM is formulated as an MRF, allowing it to benefit from the rich set of existing MRF inference methods and scale to large models and datasets. To demonstrate MAM's capabilities to capture CSIs at scale, we apply MAMs to capture an important type of CSI that is present in a symbolic approach to recurrent computations in perceptual grouping. Experiments on two recently proposed synthetic perceptual grouping tasks and on realistic images demonstrate the advantages of MAMs in sample-efficiency, interpretability and generalizability when compared with strong recurrent neural network baselines, and validate MAM's capabilities to efficiently capture CSIs at scale.


page 4

page 5

page 17

page 18

page 23


Decomposable context-specific models

We introduce a family of discrete context-specific models, which we call...

Rigorous Explanation of Inference on Probabilistic Graphical Models

Probabilistic graphical models, such as Markov random fields (MRF), expl...

Hinge-loss Markov Random Fields: Convex Inference for Structured Prediction

Graphical models for structured domains are powerful tools, but the comp...

Duality in Graphical Models

Graphical models have proven to be powerful tools for representing high-...

A new characterization of discrete decomposable models

Decomposable graphical models, also known as perfect DAG models, play a ...

Scalable Inference of Sparsely-changing Markov Random Fields with Strong Statistical Guarantees

In this paper, we study the problem of inferring time-varying Markov ran...

Tagger: Deep Unsupervised Perceptual Grouping

We present a framework for efficient perceptual inference that explicitl...

Please sign up or login with your details

Forgot password? Click here to reset