Large language models (LLMs) have demonstrated remarkable capabilities in many fields, especially in complex neural lagnuage processing tasks. Despite their impressive performance, the content generated by LLMs still suffers from the problem of hallucination, particularly in tasks that require real-time data or specialized domain knowledge. Knowledge graphs and multimodal unstructured data serve as important sources of knowledge that can help address the hallucination issues in LLMs. However, existing methods mostly utilize knowledge graphs or multimodal unstructured data in isolation, neglecting the interaction between the two and it is the interaction that contributes to the extraction of deep knowledge in the knowledge base. In this paper, we propose a novel framework called the Collaborative Framework of Multimodal Unstructured Data and Knowledge Graph (CoMuS-KG). This framework enhances the reasoning capabilities of LLMs by enabling interaction between multimodal unstructured data and knowledge graphs, extracting deep knowledge from unstructured data, and completing missing information in knowledge graphs. Specifically, CoMuS-KG first decompose the question posed to the LLMs into multiple sub-questions and convert these sub-questions into knowledge graph triplets with missing head entity, tail entity, or relation. And then the knowledge graph and multimodal unstructured data are used to complete these triplets. Finally, we use the completed triplets to answer the original question and the completed triplets can be updated back into the knowledge graph to assist in other reasoning tasks. Extensive experiments on three KGQA benchmark datasets demonstrate the question-answering performance and reasoning capabilities of CoMuS-KG. Our code is publicly available at: https://github.comlGuChongAnlCoMuS-KG

When the unknown degradation is mixed with unknown blurry kernels, how to perform super-resolution operation is an open issue. The mean idea of the existing zero-shot and non-zero-shot methods is to estimate blurry kernel. The effects of these methods depend on the accuracy of the deduced blurry kernel. In this paper, we propose Randomly initialized Zero-Shot Super-Resolution (RZSR) training strategy. RZSR is a zero-shot training method and it allows the network to extract low-resolution image features and generate its counterpart high-resolution images under the interference of degradation algorithms. We further propose two model-agnostic modules which are Adaptive Information Extraction Module (AIEM) and knowledge dictionary. They respectively assist the network to extract features and well fit the data distribution of clear images. RZSR can be applied to any single image super-resolution and video super-resolution models. We prove the generalization ability and superiority of RZSR through a series of experiments.

Graph neural networks (GNNs) have recently become increasingly popular due to their ability to learn node representations in complex graphs. Existing graph representation learning methods mainly target static graphs in Euclidean space, whereas many graphs in practical applications are dynamic and evolve continuously over time. Recent work has demonstrated that real-world graphs exhibit hierarchical properties. Unfortunately, many methods typically do not account for these latent hierarchical structures. In this work, we propose a dynamic network in hyperbolic space via self-attention, referred to as DynHAT, which leverages both the hyperbolic geometry and attention mechanism to learn node representations. More specifically, DynHAT captures hierarchical information by mapping the structural graph onto hyperbolic space, and time-varying dynamic evolution by flexibly weighting historical representations. Through extensive experiments on three real-world datasets, we show the superiority of our model in embedding dynamic graphs in hyperbolic space and competing methods in a link prediction task. In addition, our results show that embedding dynamic graphs in hyperbolic space has competitive performance when necessitating low dimensions.

Big-data applications often involve a vast number of observations and features, creating new challenges for variable selection and parameter estimation. This paper presents a novel technique called “slow kill,” which utilizes nonconvex constrained optimization, adaptive$\ell _{2}$-shrinkage, and increasing learning rates. The fact that the problem size can decrease during the slow kill iterations makes it particularly effective for large-scale variable screening. The interaction between statistics and optimization provides valuable insights into controlling quantiles, stepsize, and shrinkage parameters in order to relax the regularity conditions required to achieve the desired level of statistical accuracy. Experimental results on real and synthetic data show that slow kill outperforms state-of-the-art algorithms in various situations while being computationally efficient for large-scale data.

This paper studies the alarm response problem of false data injection (FDI) attacks for nonlinear physical dynamical process in cyber-physical systems. Considering the real-time attack detecting, multi-sensor fusion strategy is used to enhance the reliabilty which can also potentially improve the detection speed. Multiple finite-level logarithmic quantizers are used for estimators to reduce the size of data packages containing residual message due to the limited bandwidth. Then the optimal weight for each local estimator is derived by solving a predefined convex optimal problem. By using the proposed fusion method, a more accurate evaluation threshold is obtained, which further improves the performance of alarm response. At last, a simulation example of civil aircraft is used to illustrate the effectiveness of the proposed method.

Accurate intention understanding of the user inputs is the key to human-computer interaction (HCI). At present, more and more studies just focus on the improvement of algorithm efficiency and ignore the nature exploration of intention understanding. In humans, working memory is regarded as a cognitive system for handling a range of neuro-cognitive tasks. Because the intention understanding is a kind of human cognitive ability, in this paper we will explore the human cognitive execution mechanism and try to apply it to improve the machines' intention understanding level. First, we demonstrated a cognitive learning model called Cortico-Basal ganglia-Cerebella (CBC) loops plays an important role in the process of working memory. Then, based on the full understanding of the loops operation mechanism, we put forward a new model of intension understanding. Finally, we applied this model on speech data and compared it with other two methods. The results showed that the new model could help to get task-specific vectors and offer further gains in performance on intention understanding.

Neuroimaging studies of cognitive learning have identified the important roles of Cortico-Basal ganglia- Cerebellar (CBC) loops, and the neurofeedback training based on real-time functional magnetic resonance imaging (rt-fMRI) has been deemed as a kind of cognitive learning. However, how the connectivity in CBC loops change during the feedback training and the underlying learning mechanism behind the training both remain unclear. In this paper, we firstly used Granger causality model method to construct CBC loops in a working memory feedback training task by rt-fMRI. Then, we examined the interaction changes in CBC loops induced the training. The results showed that the connectivity of fronto- parietal, cortico-basal ganglia (BG) and cortico-cerebellar in CBC loops were significantly enhanced during the training in the experimental group. Further correlation analysis indicated the connectivity changes of cortico-BG were stronger positively correlated with the behavioral improvements. These findings suggest that the interaction between the cortex and BG in the feedback training is an essential factor to the behavioral improvement which makes the individual to complete cognitive learning better.