We propose a novel interactive learning framework which we refer to as Interactive Attention Learning (IAL), in which the human supervisors interactively manipulate the allocated attentions, to correct the model's behavior by updating the attention-generating network. However, such a model is prone to overfitting due to scarcity of human annotations, and requires costly retraining. Moreover, it is almost infeasible for the human annotators to examine attentions on tons of instances and features. We tackle these challenges by proposing a sample-efficient attention mechanism and a cost-effective reranking algorithm for instances and features. First, we propose Neural Attention Process (NAP), which is an attention generator that can update its behavior by incorporating new attention-level supervisions without any retraining. Secondly, we propose an algorithm which prioritizes the instances and the features by their negative impacts, such that the model can yield large improvements with minimal human feedback. We validate IAL on various time-series datasets from multiple domains (healthcare, real-estate, and computer vision) on which it significantly outperforms baselines with conventional attention mechanisms, or without cost-effective reranking, with substantially less retraining and human-model interaction cost.
Synchronous Speech Recognition and Speech-to-Text Translation with Interactive Decoding
Institute of Automation, CAS(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);Baidu Inc.(百度公司);CAS Center for Excellence in Brain Science and Intelligence Technology(中国科学院脑科学与智能技术卓越创新中心)
近年来,交互式推荐系统越来越受欢迎。通过用户与系统之间的交互,(1)用户可以主动干预推荐结果,而不是被动地接受它们,(2)系统可以更多地了解用户,以便提供更好的推荐。我们专注于单轮交互,即系统向用户提问(步骤1),并利用他的反馈来生成更好的推荐(步骤2)。本文提出了一种新的基于查询的交互式推荐系统,其中步骤1是\textbf{personalized questions are accurately generated from millions of automatically constructed questions},步骤2是\textbf{the recommendation is ensured to be closely-related to users' feedback}。我们通过将步骤1转换为查询推荐任务,将步骤2转换为检索任务来实现这一点。前一项任务是我们的主要挑战。我们首先提出了一个基于元路径的模型,以有效地从大型查询池中检索数百个查询候选。然后,一个自适应的Attention-GRU模型的开发,以有效地排名这些候选人的推荐。在中国大型电子商务平台淘宝网上进行的离线和在线实验验证了我们的交互系统的有效性。自2018年11月11日起,该系统已在淘宝App首页投入使用(在线工作方式请参见https://v.qq.com/x/page/s0833tkp1uo.ht…
The Graph-Based Behavior-Aware Recommendation for Interactive News
Peking University(北京大学);University of Chicago(芝加哥大学);National Computer Network Emergency Response Technical Team/Coordination Center of China(国家计算机网络应急技术处理协调中心)
Structure-aware Interactive Graph Neural Networks for the Prediction of Protein-Ligand Binding Affinity
University of Science and Technology of China(中国科学技术大学);Baidu Research(百度研究院);Baidu Inc.(百度公司);Baidu Research USA(百度美国研究院);Oregon State University(俄勒冈州立大学);HWL Consulting LLC(HWL咨询有限责任公司);Rutgers University(罗格斯大学)
Interactive incremental learning of generalizable skills with local trajectory modulation
German Aerospace Center (DLR)(德国航空航天中心);School of Computation, Information and Technology (CIT), Technical University of Munich (TUM)(慕尼黑工业大学计算、信息与技术学院)