Reinforced, Incremental and Cross-Lingual Event Detection From Social Messages

Revisiting low-homophily for graph-based fraud detection

The openness of Internet stimulates a large number of fraud behaviors which have become a huge threat. Graph-based fraud detectors have attracted extensive interest since the abundant structure information of graph data has proved effective. Conventional Graph Neural Network (GNN) approaches reveal fraudsters based on the homophily assumption. But fraudsters typically generate heterophilous connections and label-imbalanced neighborhood. Such behaviors deteriorate the performance of GNNs in fraud detection tasks due to the low homophily in graphs. Though some recent works have noticed the challenges, they either treat the heterophilous connections as homophilous ones or tend to reduce heterophily, which roughly ignore the benefits from heterophily. In this work, an integrated two-strategy framework HeteGAD is proposed to balance both homophily and heterophily information from neighbors. The key lies in explicitly shrinking intra-class distance and increasing inter-class segregation. Specifically, the Heterophily-aware Aggregation Strategy tease out the feature disparity on heterophilous neighbors and augment the disparity between representations with different labels. And the Homophily-aware Aggregation Strategy are devised to capture the homophilous information in global text and augment the representation similarity with the same label. Finally, two corresponding inter-relational attention mechanisms are incorporated to refine the procedure of modeling the interaction of multiple relations. Experiments are conducted to evaluate the proposed method with two real-world datasets, and demonstrate that the HeteGAD outperforms 11 state-of-the-art baselines for fraud detection.

Domain-Invariant Feature Progressive Distillation with Adversarial Adaptive Augmentation for Low-Resource Cross-Domain NER

Considering the expensive annotation in Named Entity Recognition (NER), Cross-domain NER enables NER in low-resource target domains with few or without labeled data, by transferring the knowledge of high-resource domains. However, the discrepancy between different domains causes domain shift problem hamper the performance of cross-domain NER in low-resource scenarios. In this article, we first propose an adversarial adaptive augmentation, where we integrate the adversarial strategy into a multi-task leaner to augment and qualify domain adaptive data. We extract domain-invariant features of the adaptive data to bridge the cross-domain gap and alleviate the label-sparsity problem simultaneously. Therefore, another important component in this article is the progressive domain-invariant feature distillation framework. A multi-grained MMD (Maximum Mean Discrepancy) approach in the framework to extract the multi-level domain invariant features and enable knowledge transfer across domains through the adversarial adaptive data. Advanced Knowledge Distillation (KD) schema processes progressively domain adaptation through the powerful pre-trained language models and multi-level domain invariant features. Extensive comparative experiments over 4 English and 2 Chinese benchmarks show the importance of adversarial augmentation and effective adaptation from high-resource domains to low-resource target domains. Comparison with 2 vanilla and 4 latest baselines indicates the state-of-the-art performance and superiority confronted with both zero-resource and minimal-resource scenarios.

A descriptive human visual cognitive strategy using graph neural network for facial expression recognition

In the period of rapid development on the new information technologies, computer vision has become the most common application of artificial intelligence, which is represented by deep learning in the current society. As the most direct and effective application of computer vision, facial expression recognition (FER) has become a hot topic and used in many studies and domains. However, the existing FER methods focus on deep learning to generate increasingly complex attention structures, so they are unable to consider the connotative relationship between different parts of facial expressions. Moreover, the human expression recognition method based on complex deep learning network has serious interpretability issues. Therefore, in this paper, a novel Graph Neural Network (GNN) model is proposed to consider the systematic process of FER in human visual perception. Firstly, a region division mechanism is proposed, which divides the face region into six parts to unify the selection of key facial features. On this basis, in order to better consider the connotative relationship between different parts of facial expression, a human visual cognition strategy is proposed, which uses the divided six regions to learn facial expression features, and evenly selects the key features with high reliability as graph nodes. In combination with the human regional cooperative recognition process, the connotative relationship (such as relative position and similar structure) between graph nodes is extracted, so as to construct the GNN model. Finally, the effect of FER is obtained by the modeled GNN model. The experimental results compared with other related algorithms show that the model not only has stronger characterization and generalization ability, but also has better robustness compared with state-of-the-art methods.

Knowledge-based and data-driven underground pressure forecasting based on graph structure learning

The pressure prediction technology whereby represents the rock pressure law in the excavation is fundamental to safety in production and industrial intelligentization. A growing number of researchers dedicate that machine learning is used to accurate prediction of underground pressure changes. However, the existing research which based on the classical machine learning rarely considers the cause between inducement of underground pressure and the underground pressure change. In this paper, we propose a novel Reinforced and Causal Graph Neural Network, namely RC-GNN, for the prediction task, to overcome the shortage of causal logic. First, we build a causal graph by considering internal relations between inducement and display of pressure and employ prior knowledge to erect the early and properties of the graph. Second, we construct the prediction network for underground pressure by graph convolutional networks and long short-term memory. Finally, we use the performance index of underground pressure prediction to design a reinforcement learning algorithm, which achieves optimization of the causal graph. Compared to six representative methods, experimental results with 18-60% increases in performance on the real prediction task.