FILDNE: A Framework for Incremental Learning of Dynamic Networks Embeddings

Learning attentive attribute-aware node embeddings in dynamic environments

Learning node embeddings is fundamental for numerous applications, such as link prediction and node classification. Node embeddings seek to learn a low-dimensional representation for each node in the graph. Many existing node representation learning methods for dynamic attributed graphs focus on preserving the temporal proximity of the nodes with relatively shallow models. However, real-life graphs are complex and usually exhibit evolutionary patterns of node attributes and graph structure. Therefore, the current state-of-the-art models fail to capture the information in the dynamic attributed graphs and settle for sub-optimal results. In this paper, we propose a novel model for embedding nodes in dynamic attributed graphs that captures the full extent of all relevant node information and the graph interrelations as well as graph evolutionary patterns. During model training, attribute-aware node embedding is learned using both graph and node properties in a dynamic context. Experiments demonstrate that our proposed method is superior to the state-of-the-art models in link prediction tasks. In addition, it introduces a novel way of learning richer representations by fully exploiting node attributes, graph structure, and evolutionary patterns in dynamic attributed graphs.

Incremental learning for detection in X-ray luggage perspective images

Convolutional neural networks have achieved remarkable results in the detection of X-ray luggage contraband. However, with an increase in contraband classes and substantial artificial transformation, the offline network training method has been unable to accurately detect the rapidly growing new classes of contraband. The current model cannot incrementally learn the newly appearing classes in real time without retraining the model. When the quantity of different types of contraband is not evenly distributed in the real-time detection process, the convolution neural network that is optimized by the gradient descent method will produce catastrophic forgetting, which means learning new knowledge and forgetting old knowledge, and the detection effect on the old classes will suddenly decline. To overcome this problem, this paper proposes an incremental learning method for online continuous learning of models and incrementally learns and detects new classes in the absence of old classes in the new classes. First, we perform parameter compression on the original network by distillation to ensure stable identification of the old classes. Second, the area proposal subnetwork and object detection subnetwork are incrementally learned to obtain the recognition ability of the new classes. In addition, this paper designs a new loss function, which causes the network to avoid catastrophic forgetting and stably detect the object of the new contraband classes. To reliably verify the model, this paper produces a multi-angle dataset for security perspective images. A total of 10 classes of contraband are tested, and the interference between two object detections is analyzed by model parameters. The experimental results show that the model can stably perform new contraband object learning even when there is an uneven distribution of data types.