Timezone: »

 
Poster
Submodular meets Structured: Finding Diverse Subsets in Exponentially-Large Structured Item Sets
Adarsh Prasad · Stefanie Jegelka · Dhruv Batra

Tue Dec 09 04:00 PM -- 08:59 PM (PST) @ Level 2, room 210D #None

To cope with the high level of ambiguity faced in domains such as Computer Vision or Natural Language processing, robust prediction methods often search for a diverse set of high-quality candidate solutions or proposals. In structured prediction problems, this becomes a daunting task, as the solution space (image labelings, sentence parses, etc.) is exponentially large. We study greedy algorithms for finding a diverse subset of solutions in structured-output spaces by drawing new connections between submodular functions over combinatorial item sets and High-Order Potentials (HOPs) studied for graphical models. Specifically, we show via examples that when marginal gains of submodular diversity functions allow structured representations, this enables efficient (sub-linear time) approximate maximization by reducing the greedy augmentation step to inference in a factor graph with appropriately constructed HOPs. We discuss benefits, tradeoffs, and show that our constructions lead to significantly better proposals.

Author Information

Adarsh Prasad (UT Austin)
Stefanie Jegelka (MIT)
Dhruv Batra (Georgia Tech / Facebook AI Research (FAIR))

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors