Semantic Consistent Embedding for Domain Adaptive Zero-Shot Learning.

Unsupervised domain adaptation has limitations when encountering label discrepancy between the source and target domains. While open-set domain adaptation approaches can address situations when the target domain has additional categories, these methods can only detect them but not further classify them. In this paper, we focus on a more challenging setting dubbed Domain Adaptive Zero-Shot Learning (DAZSL), which uses semantic embeddings of class tags as the bridge between seen and unseen classes to learn the classifier for recognizing all categories in the target domain when only the supervision of seen categories in the source domain is available. The main challenge of DAZSL is to perform knowledge transfer across categories and domain styles simultaneously. To this end, we propose a novel end-to-end learning mechanism dubbed Three-way Semantic Consistent Embedding (TSCE) to embed the source domain, target domain, and semantic space into a shared space. Specifically, TSCE learns domain-irrelevant categorical prototypes from the semantic embedding of class tags and uses them as the pivots of the shared space. The source domain features are aligned with the prototypes via their supervised information. On the other hand, the mutual information maximization mechanism is introduced to push the target domain features and prototypes towards each other. By this way, our approach can align domain differences between source and target images, as well as promote knowledge transfer towards unseen classes. Moreover, as there is no supervision in the target domain, the shared space may suffer from the catastrophic forgetting problem. Hence, we further propose a ranking-based embedding alignment mechanism to maintain the consistency between the semantic space and the shared space. Experimental results on both I2AwA and I2WebV clearly validate the effectiveness of our method. Code is available at https://github.com/tiggers23/TSCE-Domain-Adaptive-Zero-Shot-Learning.

Progressive Multigranularity Information Propagation for Coupled Aspect-Opinion Extraction.

Coupled aspect-opinion extraction aims to identify aspect-opinion pairs in the form of (aspect term, opinion term) or triplets in the form of (aspect term, opinion term, sentiment polarity) from user-generated texts. Compared to the traditional aspect-based sentiment prediction or extraction tasks, coupled aspect-opinion extraction needs to associate aspects with their corresponding opinions and organize opinion-related information into structured outputs. The existing works either divide this task into subproblems (i.e., term extraction and relation prediction) or utilize a unified tagging scheme. However, these methods only focus on atomic word-level interactions and ignore the intensive information propagation among different granularities (e.g., words and word pairs). To address this limitation, we propose a progressive multigranularity information propagation network that progressively explores three types of correlations with different granularities. Specifically, our model starts with the most basic word-level correlations by composing all possible word pairs. In the second stage, the pairwise relation information is used to update the word features. The last stage propagates information among word pairs to produce the relation scores. We treat the task as a unified relation prediction problem and construct an end-to-end framework that iteratively conducts the three-stage information propagation to refine the textual representations. Comprehensive experiments on different aspect-based sentiment analysis benchmarks clearly demonstrate the effectiveness of the proposed approach.

Spatiotemporal variations of air pollutants and ozone prediction using machine learning algorithms in the Beijing-Tianjin-Hebei region from 2014 to 2021.

China was seriously affected by air pollution in the past decade, especially for particulate matter (PM) and emerging ozone pollution recently. In this study, we systematically examined the spatiotemporal variations of six air pollutants and conducted ozone prediction using machine learning (ML) algorithms in the Beijing-Tianjin-Hebei (BTH) region. The annual-average concentrations of CO, PM10, PM2.5 and SO2 decreased at a rate of 141, 11.0, 6.6 and 5.6 µg/m3/year, while a pattern of initial increase and later decrease was observed for NO2 and O3_8 h. The concentration of SO2, CO and NO2 was higher in Tangshan and Xingtai, while northern BTH region has lower levels of CO, NO2 and PM. Spatial variations of ozone were relatively small in the BTH region. Monthly variations of PM10 displayed an increase in March probably due to wind-blown dusts from Northwest China. A seasonal and diurnal pattern with summer and afternoon peaks was found for ozone, which was contrast with other pollutants. Further ML algorithms such as Random Forest (RF) model and Decision tree (DT) regression showed good ozone prediction performance (daily: R2 = 0.83 and 0.73, RMSE = 30.0 and 37.3 µg/m3, respectively; monthly: R2 = 0.93 and 0.88, RMSE = 12.1 and 15.8 µg/m3, respectively) based on 10-fold cross-validation. Both RF model and DT regression relied more on the spatial trend as higher temporal prediction performance was achieved. Solar radiation- and temperature-related variables presented high importance at daily level, whereas sea level pressure dominated at monthly level. The spatiotemporal heterogeneity in variable importance was further confirmed using case studies based on RF model. In addition, variable importance was possibly influenced by the emission reductions due to COVID-19 pandemic. Despite its possible weakness to capture ozone extremes, RF model was beneficial and suggested for predicting spatiotemporal variations of ozone in future studies.

Weakly Supervised Domain Adaptation for Aspect Extraction via Multilevel Interaction Transfer.

Fine-grained aspect term extraction is an essential subtask in aspect-based opinion analysis. It aims to identify the aspect terms (also known as opinion targets) of a product or service in each sentence. To learn a good aspect extraction model, an expensive annotation process is usually involved to acquire sufficient token-level labels for each domain, which is not realistic. To address this limitation, some previous works propose domain adaptation strategies to transfer knowledge from a sufficiently labeled source domain to unlabeled target domains. However, due to both the difficulty of fine-grained prediction problems and the large domain gap between different domains, the performance is still far from satisfactory. In this work, we conduct a pioneer study on leveraging sentence-level aspect category labels that can be usually available in commercial services, such as review sites or social media to promote token-level transfer for extraction purpose. Specifically, the aspect category information can be used to construct pivot knowledge for transfer with the assumption that the interactions between the sentence-level aspect category and the token-level aspect terms are invariant across domains. To this end, we propose a novel multilevel reconstruction mechanism that aligns both the fine- and coarse-grained information in multiple levels of abstractions. Comprehensive experiments over several benchmark data sets clearly demonstrate that our approach can fully utilize the sentence-level aspect category labels to improve cross-domain aspect term extraction with a large performance gain.

Breast tumor classification through learning from noisy labeled ultrasound images.

PURPOSE: To train deep learning models to differentiate benign and malignant breast tumors in ultrasound images, we need to collect many training samples with clear labels. In general, biopsy results can be used as benign/malignant labels. However, most clinical samples generally do not have biopsy results. Previous works have proposed generating benign/malignant labels according to Breast Imaging, Reporting and Data System (BI-RADS) ratings. However, this approach will cause noisy labels, which means that the benign/malignant labels produced from BI-RADS diagnoses may be inconsistent with the ground truths. Consequently, deep models will overfit the noisy labels and hence obtain poor generalization performance. In this work, we mainly focus on how to reduce the negative effect of noisy labels when they are used to train breast tumor classification models. METHODS: We propose an effective approach called noise filter network (NF-Net) to address the problem of noisy labels when training breast tumor classification models. Specifically, to prevent deep models from overfitting the noisy labels, we propose incorporating two softmax layers for classification. Additionally, to strengthen the effect of clean labels, we design a teacher-student module for distilling the knowledge of clean labels. RESULTS: We conduct extensive comparisons with the existing works on addressing noisy labels. Our method achieves a classification accuracy of 73%, with a precision of 69%, recall of 80%, and F1-score of 0.74. This result is significantly better than those of the existing state-of-the-art works on addressing noisy labels. CONCLUSIONS: This work provides a means to overcome the label shortage problem in training breast tumor classification models. Specifically, we can generate benign/malignant labels according to the BI-RADS ratings. Although this approach will cause noisy labels, the design of NF-Net can effectively reduce the negative effect of such labels.