1.5k citations · 2.9k across the 32 of their papers we have counts for
9 papers · 1 filter
Invariant Rationalization
Shiyu Chang, Yang Zhang, Mo Yu +1
Selective rationalization improves neural network interpretability by identifying a small subset of input features -- the rationale -- that best explains or supports the prediction…
Generalizable Resource Allocation in Stream Processing via Deep Reinforcement Learning
Xiang Ni, Jing Li, Mo Yu +2
This paper considers the problem of resource allocation in stream processing, where continuous data flows must be processed in real time in a large distributed system. To maximize…
A Game Theoretic Approach to Class-wise Selective Rationalization
Shiyu Chang, Yang Zhang, Mo Yu +1
Selection of input features such as relevant pieces of text has become a common technique of highlighting how complex neural predictors operate. The selection can be optimized post…
An Efficient and Margin-Approaching Zero-Confidence Adversarial Attack
Yang Zhang, Shiyu Chang, Mo Yu +1
There are two major paradigms of white-box adversarial attacks that attempt to impose input perturbations. The first paradigm, called the fix-perturbation attack, crafts adversaria…
Cross-lingual Knowledge Graph Alignment via Graph Matching Neural Network
Kun Xu, Liwei Wang, Mo Yu +4
Previous cross-lingual knowledge graph (KG) alignment studies rely on entity embeddings derived only from monolingual KG structural information, which may fail at matching entities…
DAG-GNN: DAG Structure Learning with Graph Neural Networks
Yue Yu, Jie Chen, Tian Gao +1
Learning a faithful directed acyclic graph (DAG) from samples of a joint distribution is a challenging combinatorial problem, owing to the intractable search space superexponential…