More Like this

1. Deep Transfer Reinforcement Learning for Text Summarization

   https://doi.org/10.1137/1.9781611975673.76  

   Keneshloo, Yaser; Ramakrishnan, Naren; Reddy, Chandan K. (April 2019, Proceedings of SIAM International Conference on Data Mining (SDM))

   Deep neural networks are data hungry models and thus face difficulties when attempting to train on small text datasets. Transfer learning is a potential solution but their effectiveness in the text domain is not as explored as in areas such as image analysis. In this paper, we study the problem of transfer learning for text summarization and discuss why existing state-of-the-art models fail to generalize well on other (unseen) datasets. We propose a reinforcement learning framework based on a self-critic policy gradient approach which achieves good generalization and state-ofthe-art results on a variety of datasets. Through an extensive set of experiments, we also show the ability of our proposed framework to fine-tune the text summarization model using only a few training samples. To the best of our knowledge, this is the first work that studies transfer learning in text summarization and provides a generic solution that works well on unseen data 

   more » « less
2. Recursive neural programs: A differentiable framework for learning compositional part-whole hierarchies and image grammars

   https://doi.org/10.1093/pnasnexus/pgad337  

   Fisher, Ares; Rao, Rajesh P (November 2023, PNAS Nexus)

   Abbott, Derek (Ed.)

   Abstract Human vision, thought, and planning involve parsing and representing objects and scenes using structured representations based on part-whole hierarchies. Computer vision and machine learning researchers have recently sought to emulate this capability using neural networks, but a generative model formulation has been lacking. Generative models that leverage compositionality, recursion, and part-whole hierarchies are thought to underlie human concept learning and the ability to construct and represent flexible mental concepts. We introduce Recursive Neural Programs (RNPs), a neural generative model that addresses the part-whole hierarchy learning problem by modeling images as hierarchical trees of probabilistic sensory-motor programs. These programs recursively reuse learned sensory-motor primitives to model an image within different spatial reference frames, enabling hierarchical composition of objects from parts and implementing a grammar for images. We show that RNPs can learn part-whole hierarchies for a variety of image datasets, allowing rich compositionality and intuitive parts-based explanations of objects. Our model also suggests a cognitive framework for understanding how human brains can potentially learn and represent concepts in terms of recursively defined primitives and their relations with each other. 

   more » « less
3. Few-shot Relational Reasoning via Connection Subgraph Pretraining

   Huang, Qian; Ren, Hongyu; Leskovec, Jure (December 2022, Advances in Neural Information Processing Systems)

   Few-shot knowledge graph (KG) completion task aims to perform inductive reasoning over the KG: given only a few support triplets of a new relation R (e.g., (chop, R, kitchen), (read, R, library)), the goal is to predict the query triplets of the same unseen relation R, e.g., (sleep, R, ?). Current approaches cast the problem in a meta-learning framework, where the model needs to be first jointly trained over many training few-shot tasks, each being defined by its own relation, so that learning/prediction on the target few-shot task can be effective. However, in real-world KGs, curating many training tasks is a challenging ad hoc process. We proposed Connection Subgraph Reasoner (CSR), which can make predictions for the target few-shot task directly without the need for pre-training on the human curated set of training tasks. The key to CSR is that we explicitly model a shared connection subgraph between support and query triplets, as inspired by the principle of eliminative induction. To adapt to specific KG, we design a corresponding self-supervised pretraining scheme with the objective of reconstructing automatically sampled connection subgraphs. Our pretrained model can then be directly applied to target few-shot tasks without the need for training few-shot tasks. Extensive experiments on real KGs, including NELL, FB15K-237, and ConceptNet, demonstrate the effectiveness of our framework: we have shown that even a learning-free implementation of CSR can already perform competitively to existing methods on target few-shot tasks; with pretraining, CSR can achieve significant gains of up to 52% on the more challenging inductive few-shot tasks where the entities are also unseen during (pre)training. 

   more » « less
4. Adaptive Privacy Preserving Deep Learning Algorithms for Medical Data

   Zhang, Xinyue; Ding, Jiahao; Wu, Maoqiang; Wong, Stephen TC.; Nguyen, Hien V.; Pan, Miao (January 2021, IEEE Winter Conference on Applications of Computer Vision)

   null (Ed.)

   Deep learning holds a great promise of revolutionizing healthcare and medicine. Unfortunately, various inference attack models demonstrated that deep learning puts sensitive patient information at risk. The high capacity of deep neural networks is the main reason behind the privacy loss. In particular, patient information in the training data can be unintentionally memorized by a deep network. Adversarial parties can extract that information given the ability to access or query the network. In this paper, we propose a novel privacy-preserving mechanism for training deep neural networks. Our approach adds decaying Gaussian noise to the gradients at every training iteration. This is in contrast to the mainstream approach adopted by Google's TensorFlow Privacy, which employs the same noise scale in each step of the whole training process. Compared to existing methods, our proposed approach provides an explicit closed-form mathematical expression to approximately estimate the privacy loss. It is easy to compute and can be useful when the users would like to decide proper training time, noise scale, and sampling ratio during the planning phase. We provide extensive experimental results using one real-world medical dataset (chest radiographs from the CheXpert dataset) to validate the effectiveness of the proposed approach. The proposed differential privacy based deep learning model achieves significantly higher classification accuracy over the existing methods with the same privacy budget. 

   more » « less
5. Forecasting Traffic Speed during Daytime from Google Street View Images using Deep Learning

   https://doi.org/10.1177/03611981231169531  

   Jiao, Junfeng; Wang, Huihai (May 2023, Transportation Research Record: Journal of the Transportation Research Board)

   Traffic forecasting plays an important role in urban planning. Deep learning methods outperform traditional traffic flow forecasting models because of their ability to capture spatiotemporal characteristics of traffic conditions. However, these methods require high-quality historical traffic data, which can be both difficult to acquire and non-comprehensive, making it hard to predict traffic flows at the city scale. To resolve this problem, we implemented a deep learning method, SceneGCN, to forecast traffic speed at the city scale. The model involves two steps: firstly, scene features are extracted from Google Street View (GSV) images for each road segment using pretrained Resnet18 models. Then, the extracted features are entered into a graph convolutional neural network to predict traffic speed at different hours of the day. Our results show that the accuracy of the model can reach up to 86.5% and the Resnet18 model pretrained by Places365 is the best choice to extract scene features for traffic forecasting tasks. Finally, we conclude that the proposed model can predict traffic speed efficiently at the city scale and GSV images have the potential to capture information about human activities. 

   more » « less