Le Song

Towards Black-box Iterative Machine Teaching

2017 · arXiv (Cornell University)

In this paper, we make an important step towards the black-box machine teaching by considering the cross-space machine teaching, where the teacher and the learner use different feature representations and the teacher can not fully …

Intention Propagation for Multi-agent Reinforcement Learning

2021

A hallmark of an AI agent is to mimic human beings to understand and interact with others. In this paper, we propose a \emph{collaborative} multi-agent reinforcement learning algorithm to learn a \emph{joint} policy through the …

DC-BERT: Decoupling Question and Document for Efficient Contextual Encoding

2020

Recent studies on open-domain question answering have achieved prominent performance improvement using pre-trained language models such as BERT. State-of-the-art approaches typically follow the "retrieve and read" pipeline and employ BERT-based reranker to filter retrieved documents …

Understanding Deep Architectures with Reasoning Layer

2020 · arXiv (Cornell University)

Recently, there has been a surge of interest in combining deep learning models with reasoning in order to handle more sophisticated learning tasks. In many cases, a reasoning task can be solved by an iterative …

A Framework For Differentiable Discovery Of Graph Algorithms

2021

Recently there is a surge of interests in using graph neural networks (GNNs) to learn algorithms. However, these works focus more on imitating existing algorithms, and are limited in two important aspects: the search space …

Variational Reasoning for Question Answering With Knowledge Graph

2018 · Proceedings of the AAAI Conference on Artificial Intelligence

Knowledge graph (KG) is known to be helpful for the task of question answering (QA), since it provides well-structured relational information between entities, and allows one to further infer indirect facts. However, it is challenging …

Variational Reasoning for Question Answering with Knowledge Graph

2017 · arXiv (Cornell University)

Knowledge graph (KG) is known to be helpful for the task of question answering (QA), since it provides well-structured relational information between entities, and allows one to further infer indirect facts. However, it is challenging …