Industry
Hierarchical Reinforcement Learning for Zero-shot Generalization with Subtask Dependencies
Sungryull Sohn, Junhyuk Oh, Honglak Lee
Neural Information Processing Systems http://nips.cc/
A Generalized Algorithm for Multi-Objective Reinforcement Learning and Policy Adaptation
Runzhe Yang, Xingyuan Sun, Karthik Narasimhan
Neural Information Processing Systems http://nips.cc/
Overleaf Example
Deep networks have shown remarkable results in the task of object detection. However, their performance suffers critical drops when they are subsequently trained on novel classes without any sample from the base classes originally used to train the model. This phenomenon is known as catastrophic forgetting. Recently, several incremental learning methods are proposed to mitigate catastrophic forgetting for object detection. Despite the effectiveness, these methods require co-occurrence of the unlabeled base classes in the training data of the novelclasses. This requirement isimpractical in manyreal-world settings since the base classes do not necessarily co-occur with the novel classes.
Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks
Yaqin Zhou, Shangqing Liu, Jingkai Siow, Xiaoning Du, Yang Liu
Neural Information Processing Systems http://nips.cc/
ffbd6cbb019a1413183c8d08f2929307-Supplemental.pdf
The numbers of the lower and upper bounds in the binarization layer are both in{5,10,50}. We utilize the Adam (Kingma and Ba, 2014) method for the training process with a mini-batch size of 32. Onlargedata sets, RRL is trained for 100 epochs, and we decay the learning rate by a factor of 0.75 every 20 epochs. Theinverse of regularization strength is in {1, 4, 16, 32}. Figure 7 shows the scatter plots of F1 score against log(#edges) for rule-based models trained on the other ten data sets.