An official website of the United States government
Neural models have become one of the most important approaches to dialog response generation. However, they still tend to generate the most common and generic responses in the corpus all the time. To address this problem, we designed an iterative training process and ensemble method based on boosting. We combined our method with different training and decoding paradigms as the base model, including mutual-information-based decoding and reward-augmented maximum likelihood learning. Empirical results show that our approach can significantly improve the diversity and relevance of the responses generated by all base models, backed by objective measurements and human evaluation.
more »
« less
Benchmark of DNN Model Search at Deployment Time
Deep learning has become the most popular direction in machine learning and artificial intelligence. However, the preparation of training data, as well as model training, are often time-consuming and become the bottleneck of the end-to-end machine learning lifecycle. Reusing models for inferring a dataset can avoid the costs of retraining. However, when there are multiple candidate models, it is challenging to discover the right model for reuse. Although there exist a number of model-sharing platforms such as ModelDB, TensorFlow Hub, PyTorch Hub, and DLHub, most of these systems require model uploaders to manually specify the details of each model and model downloaders to screen keyword search results for selecting a model. We are lacking a highly productive model search tool that selects models for deployment without the need for any manual inspection and/or labeled data from the target domain. This paper proposes multiple model search strategies including various similarity-based approaches and non-similarity-based approaches. We design, implement and evaluate these approaches on multiple model inference scenarios, including activity recognition, image recognition, text classification, natural language processing, and entity matching. The experimental evaluation showed that our proposed asymmetric similarity-based measurement, adaptivity, outperformed symmetric similarity-based measurements and non-similarity-based measurements in most of the workloads.
more »
« less
- Award ID(s):
- 2144923
- PAR ID:
- 10426127
- Date Published:
- Journal Name:
- SSDBM '22: Proceedings of the 34th International Conference on Scientific and Statistical Database Management
- Page Range / eLocation ID:
- 1 to 12
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Recently, there has been a major emphasis on developing data-driven approaches involving machine learning (ML) for high-speed static state estimation (SE) in power systems. The emphasis stems from the ability of ML to overcome difficulties associated with model-based approaches, such as handling of non-Gaussian measurement noise. However, topology changes pose a stiff challenge for performing ML-based SE because the training and test environments become different when such changes occur. This paper circumvents this challenge by formulating a graph neural network (GNN)-based time-synchronized state estimator that considers the physical connections of the power system during the training itself. The results obtained using the IEEE 118-bus system indicate that the GNN-based state estimator outperforms both the model-based linear state estimator and a data-driven deep neural network-based state estimator in the presence of non-Gaussian measurement noise and topology changes, respectively.more » « less
-
Physics-guided machine learning (PGML) has become a prevalent approach in studying scientific systems due to its ability to integrate scientific theories for enhancing machine learning (ML) models. However, most PGML approaches are tailored to isolated and relatively simple tasks, which lim- its their applicability to complex systems involving multiple interacting processes and numerous influencing features. In this paper, we propose a Physics-Guided Foundation Model (PGFM) that combines pre-trained ML models and physics- based models and leverages their complementary strengths to improve the modeling of multiple coupled processes. To effectively conduct pre-training, we construct a simulated en- vironmental system that encompasses a wide range of influ- encing features and various simulated variables generated by physics-based models. The model is pre-trained in this sys- tem to adaptively select important feature interactions guided by multi-task objectives. We then fine-tune the model for each specific task using true observations, while maintaining con- sistency with established physical theories, such as the prin- ciples of mass and energy conservation. We demonstrate the effectiveness of this methodology in modeling water temper- ature and dissolved oxygen dynamics in real-world lakes. The proposed PGFM is also broadly applicable to a range of sci- entific fields where physics-based models are being used.more » « less
-
Physics-guided machine learning (PGML) has become a prevalent approach in studying scientific systems due to its ability to integrate scientific theories for enhancing machine learning (ML) models. However, most PGML approaches are tailored to isolated and relatively simple tasks, which limits their applicability to complex systems involving multiple interacting processes and numerous influencing features. In this paper, we propose a Physics-Guided Foundation Model (PGFM) that combines pre-trained ML models and physics-based models and leverages their complementary strengths to improve the modeling of multiple coupled processes. To effectively conduct pre-training, we construct a simulated environmental system that encompasses a wide range of influencing features and various simulated variables generated by physics-based models. The model is pre-trained in this system to adaptively select important feature interactions guided by multi-task objectives. We then fine-tune the model for each specific task using true observations, while maintaining consistency with established physical theories, such as the principles of mass and energy conservation. We demonstrate the effectiveness of this methodology in modeling water temperature and dissolved oxygen dynamics in real-world lakes. The proposed PGFM is also broadly applicable to a range of scientific fields where physics-based models are being used.more » « less
-
Accurately predicting the ridership of public-transit routes provides substantial benefits to both transit agencies, who can dispatch additional vehicles proactively before the vehicles that serve a route become crowded, and to passengers, who can avoid crowded vehicles based on publicly available predictions. The spread of the coronavirus disease has further elevated the importance of ridership prediction as crowded vehicles now present not only an inconvenience but also a public-health risk. At the same time, accurately predicting ridership has become more challenging due to evolving ridership patterns, which may make all data except for the most recent records stale. One promising approach for improving prediction accuracy is to fine-tune the hyper-parameters of machine-learning models for each transit route based on the characteristics of the particular route, such as the number of records. However, manually designing a machine-learning model for each route is a labor-intensive process, which may require experts to spend a significant amount of their valuable time. To help experts with designing machine-learning models, we propose a neural-architecture and feature search approach, which optimizes the architecture and features of a deep neural network for predicting the ridership of a public-transit route. Our approach is based on a randomized local hyper-parameter search, which minimizes both prediction error as well as the complexity of the model. We evaluate our approach on real-world ridership data provided by the public transit agency of Chattanooga, TN, and we demonstrate that training neural networks whose architectures and features are optimized for each route provides significantly better performance than training neural networks whose architectures and features are generic.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Paper:
- https://doi.org/10.1145/3538712.3538725
