Traditional physics-informed deep learning combines the data-driven methods with the model-based methods by incorporating physics loss as a constraint in total loss function, which aims to enforce the neural network to behave according to the physics laws. However, the potential of physical knowledge is severely underestimated by this approach. Firstly, the physical knowledge fails to demonstrate its intended effects since the physics loss could have extremely small magnitude, more fluctuating convergence rates, and conflicting directions of the gradients compared to the data loss. Secondly, existing methods implicitly employ physics laws as auxiliary terms, which ignores that explicitly utilizing certain properties of physics laws can compensate for the shortcomings of data-driven models, particularly with regard to the data noise and relationships between variables. To alleviate these issues, we propose a Twin-Propeller Network (TPN) to realize fully message exchange among physical knowledge and data information, that releases the potential of the physics laws. Practically, we independently train data-driven model and physics-based model as two student models to get the information separated. Considering the measurement noise present in the data-driven model and the relatively robust physics-based model, we quantify the data uncertainty and utilize it as a weight to balance the two students in a integrated robust teacher model. The stronger teacher in turn transfers the respective knowledge to another student, where we innovatively propose traffic state relation distillation and physical knowledge distillation to guide the training of the data student and the physics student respectively. Through extensive experiments on both synthetic and real-world datasets, our model demonstrates better performance than the existing state-of-the-art methods.

Since the advent of virtual reality (VR), it has been implemented in medical education for surgical training and anatomy education so that the Internet of Medical Things (IoMT) could be further boosted. There have been rare studies on the research trends of the evaluation of endoscopic training through different XR modalities. Position-based dynamics (PBD) has been utilized to optimize the surgical thread simulation, This paper aims to quantitatively evaluate the training performance of each XR modality in general and in terms of the medical fields studied and outcomes measured. Sensors and devices are utilized to form the Internet of Medical Things for healthcare, where the data is uploaded to the cloud and then analyzed as follows before being fed back to the doctor so that he or she can understand his or her level of operation. Through subjective and objective evaluation, the potential promoting effects of vision and touch in module training were discussed.

Graph Convolutional Networks (GCNs) have made outstanding achievements in many tasks on graphs in recent years, but their success relies on sufficient training data. In practice, sparsely labeled graphs widely exist in the real world so self-training methods have become popular approaches by adding pseudo labeled nodes to enhance the performance of GCNs. However, we observe that most selected high-confidence pseudo labeled nodes by the existing methods would surround the true labeled nodes. It is what we called pseudo label over-dependence, which could lead to the non-uniform pseudo label distribution. Furthermore, a thorough experiment shows that the classification accuracy changes significantly under different label densities and the label-sparse regions show great potential improvement in the model performance. Based on the above findings, we theoretically analyze the constraint factors in the label-sparse regions and further propose reducing the feature distribution difference between the label-dense regions and label-sparse regions can effectively decrease the classification error. Thus, in this paper, we propose a novel Graph Label Information Migration framework (GLIM) to liberate pseudo labels from over-dependence. Specifically, we first propose a training dynamics module (TDM) that uses abundant training process information to find more reliable node labels and improve the model robustness against label noise. Then we propose a label migration module (LMM) that migrates label information from label-dense regions to label-sparse regions by a spectral based graph matching algorithm. These migrated labels are like the glimmers in the darkness, providing the supervision signals for the unlabeled nodes in label-sparse regions. Finally, we conduct extensive experiments to demonstrate the effectiveness of the proposed GLIM.

Multi-turn dialogue system has attracted increasing attention in both academic and industry community. Multi-turn dialogue generation task is a challenging work as the relations among words, utterances and external knowledge are extremely complex. However, the existing methods only focus on constructing the relations between current utterance and historical utterances, and they even oversimplify the relation mining process. Moreover, with the accumulation of dialogue information, the deep semantic information is difficult to understand so that it needs a mechanism with the ability of reasoning and digesting information repeatedly, which is ignored by previous methods. In order to solve the above problems, we propose a Memory Graph with Message Rehearsal (MGMR) for dialogue generation based on the cognitive process of human memory. MGMR contains three main modules: sensory memory, short-term memory and long-term memory. Sensory memory converts the current utterance into embeddings from both word-level and sentence-level. We design a message rehearsal module in short-term memory to extract valuable information of current utterance deeply and repeatedly combined with the relative historical dialogue information and external knowledge stored in long-term memory. Furthermore, we innovatively design a memory graph in long-term memory to construct the relations among words, utterances and knowledge. The memory graph achieves three goals: extracting accurate relations between current utterance and historical utterances, updating the historical dialogue information, and achieving knowledge precipitation by expanding memory graph with the key words and relevant external knowledge of current utterance. We evaluate our model on real-world datasets and achieve better performance compared with the existing state-of-the-art methods.