Few-Shot Continual Learning via Flat-to-Wide Approaches.

The existing approaches on continual learning (CL) call for a lot of samples in their training processes. Such approaches are impractical for many real-world problems having limited samples because of the overfitting problem. This article proposes a few-shot CL approach, termed flat-to-wide approach (FLOWER), where a flat-to-wide learning process finding the flat-wide minima is proposed to address the catastrophic forgetting (CF) problem. The issue of data scarcity is overcome with a data augmentation approach making use of a ball-generator concept to restrict the sampling space into the smallest enclosing ball. Our numerical studies demonstrate the advantage of FLOWER achieving significantly improved performances over prior arts notably in the small base tasks. For further study, source codes of FLOWER, competitor algorithms, and experimental logs are shared publicly in https://github.com/anwarmaxsum/FLOWER.

Efficient Machine Reading Comprehension for Health Care Applications: Algorithm Development and Validation of a Context Extraction Approach.

BACKGROUND: Extractive methods for machine reading comprehension (MRC) tasks have achieved comparable or better accuracy than human performance on benchmark data sets. However, such models are not as successful when adapted to complex domains such as health care. One of the main reasons is that the context that the MRC model needs to process when operating in a complex domain can be much larger compared with an average open-domain context. This causes the MRC model to make less accurate and slower predictions. A potential solution to this problem is to reduce the input context of the MRC model by extracting only the necessary parts from the original context. OBJECTIVE: This study aims to develop a method for extracting useful contexts from long articles as an additional component to the question answering task, enabling the MRC model to work more efficiently and accurately. METHODS: Existing approaches to context extraction in MRC are based on sentence selection strategies, in which the models are trained to find the sentences containing the answer. We found that using only the sentences containing the answer was insufficient for the MRC model to predict correctly. We conducted a series of empirical studies and observed a strong relationship between the usefulness of the context and the confidence score output of the MRC model. Our investigation showed that a precise input context can boost the prediction correctness of the MRC and greatly reduce inference time. We proposed a method to estimate the utility of each sentence in a context in answering the question and then extract a new, shorter context according to these estimations. We generated a data set to train 2 models for estimating sentence utility, based on which we selected more precise contexts that improved the MRC model's performance. RESULTS: We demonstrated our approach on the Question Answering Data Set for COVID-19 and Biomedical Semantic Indexing and Question Answering data sets and showed that the approach benefits the downstream MRC model. First, the method substantially reduced the inference time of the entire question answering system by 6 to 7 times. Second, our approach helped the MRC model predict the answer more correctly compared with using the original context (F1-score increased from 0.724 to 0.744 for the Question Answering Data Set for COVID-19 and from 0.651 to 0.704 for the Biomedical Semantic Indexing and Question Answering). We also found a potential problem where extractive transformer MRC models predict poorly despite being given a more precise context in some cases. CONCLUSIONS: The proposed context extraction method allows the MRC model to achieve improved prediction correctness and a significantly reduced MRC inference time. This approach works technically with any MRC model and has potential in tasks involving processing long texts.

Coordinating the Bidding Strategy in Multiissue Multiobject Negotiation With Single and Multiple Providers.

This paper addresses the problem of flexible procurement of multiple distinct services characterized by multiple nonfunctional characteristics, i.e., quality-of-service attributes. We consider the one-to-many negotiation approach as a flexible method for procuring multiple different services by a buyer agent. We address the problem of coordinating the bidding strategy amongst multiple concurrent negotiations and propose novel dynamic negotiation strategies. The proposed strategies consider the behaviors of the opponents of the current negotiation encounter in managing the local reservation values of the common negotiation issues (attributes) of different services. Most previous works consider the problem of negotiation over a single object characterized by one or more issues. We extend our previous work and investigate a more complex situation where a buyer agent negotiates over multiple distinct services given that each service has multiple negotiation issues and multiple possible providers. The experimental results show evidence for the effectiveness and robustness of our dynamic negotiation strategies under various negotiation environments.