Knowledge representation learning achieves the automatic completion of knowledge graphs (KGs) by embedding entities into continuous low-dimensional vector space. In knowledge graph completion (KGC) ...tasks, the inter-dependencies and hierarchical information in KGs have gained attention. Existing methods do not well capture the latent dependencies between all components of entities and relations. To address this, we introduce the mathematical theories of octonion, a more expressive generalized form of complex number and quaternion, and propose a translation-based KGC model with octonion (TransO). TransO models entities as octonion coordinate vectors, relations as the combination of octonion component matrices and coordinate vectors, and uses specific grouping calculation rules to interact between entities and relations. In addition, since hyperbolic Poincaré space in non-Euclidean mathematics can represent hierarchical data more accurately and effectively than traditional Euclidean space, we propose a Poincaré-extended TransO model (PTransO). PTransO transforms octonion coordinate vectors into hyperbolic embeddings by exponential mapping, and integrates the Euclidean-based calculations into hyperbolic space by operations such as Möbius addition and hyperbolic distance. The experimental results of link prediction indicate that TransO outperforms other translation-based models on the WN18 benchmark, and PTransO further achieves state-of-the-art performance in low-dimensional space on the well-established WN18RR and FB15k-237 benchmarks.
Amid the gradual increase of wind power generation, how to relieve the pressure of peak load and frequency regulation to the power system by wind power forecasting to make it run steadily becomes a ...key issue. Due to the continuous development of the field of artificial intelligence, neural network, as a machine learning technology, has shown a good predictive effect in time series data forecasting. Long-term short-term Memory is a kind of time recursive neural network, which is suitable for processing and predicting events with relatively Long intervals and delays in time series. This paper proposes an improved Long Short-Term Memory-enhanced forget-gate network model, abbreviated as LSTM-EFG, used to forecasting wind power. Based on the correlation, the features data of turbine groups in certain distance are filtered to further optimize the forecasting effect on wind power by clustering. The results show that the method with Spectral Clustering has an higher accuracy with an increase of 18.3% than those of the other forecasting models, and at the same time the convergence process has been sped up.
•An improved Long Short-Term Memory network is proposed for wind power forecasting.•This improved model enhances effect of forget-gate and optimize convergence speed.•A new wind feature extraction method is proposed to optimize the forecasting effect.•The results show this method can increase accuracy of 18.3% than those of the others.
Most knowledge graph completion methods focus on predicting existing relationships in the knowledge graph but cannot predict unseen relationships. To solve this problem, knowledge graph zero-shot ...relational learning (KGZSL) has gotten more and more attention in recent years. The common method of KGZSL is to leverage Generative Adversarial Networks (GANs) to build the connection between existing relation descriptions and knowledge graph domains. However, the traditional KGZSL method ignores the gap between relation text description and relation structured representation. To bridge this gap, we propose a Structure-Enhanced Generative Adversarial Network (SEGAN). SEGAN adopts a structure encoder to introduce knowledge graph structure information into the generator and guide the generator to generate knowledge graph embeddings more accurately. In addition, in the KGZSL task, the representations of entities are closely tied to the existing relationships, which has a negative impact on the prediction of new instances. Therefore, we design a new plug-and-play feature encoder to decouple entities from existing relationships. Experimental results on the knowledge graph zero-shot relational learning dataset demonstrate that our method has better structure representation ability, and the model performance is improved by 36.3% compared with the current optimal model.
In temporal knowledge graphs (TKGs), the status of facts is intricately tied to the dynamic and precise nature of temporal factors. Existing research merely treats time as supplementary information, ...without considering the latent semantic changes caused by the positional changes of entities within specific relations in a temporal context. Furthermore, due to the coarse granularity of timestamps in existing TKGs, the number of multiple relations pattern among entities significantly increases, limiting model performance. This paper proposes a Time-Evolving Information and Latent Semantics model (TELS), which represents facts as dual quaternion embeddings to provide a compact and elegant representation. Specifically, we use timestamp dual quaternions, transforming the entity and relation into temporal entity and temporal relation through dual quaternion multiplication. Besides, we introduce semantic-aware dual quaternion to capture the latent semantics arising from the positional changes of entities within specific relations. Next, TELS consists of two parts: (a) We use semantic-aware dual quaternions to perform transformations on head entity and tail entity respectively through dual quaternion multiplication. Next, we utilize temporal relation to transform head entity to tail entity through dual quaternion multiplication. (b) We adopt an evolutionary hierarchical factor to encapsulate the differences in modulus distribution between the temporal head entity and temporal tail entity. In this way, TELS not only uses dual quaternions to handle key patterns and multiple relations pattern, but also handles evolutionary hierarchical patterns by capturing the modulus distribution differences between temporal entities. Meanwhile, TELS learns semantic-aware dual quaternion embeddings to capture the latent semantics endowed by relations to entities. Empirically, TELS can boost the performance over seven temporal knowledge graph benchmarks.
The main objective of the work described here was to train a semantic segmentation model using classification data for thyroid nodule ultrasound images to reduce the pressure of obtaining pixel-level ...labeled data sets. Furthermore, we improved the segmentation performance of the model by mining the image information to narrow the gap between weakly supervised semantic segmentation (WSSS) and fully supervised semantic segmentation.
Most WSSS methods use a class activation map (CAM) to generate segmentation results. However, the lack of supervision information makes it difficult for a CAM to highlight the object region completely. Therefore, we here propose a novel foreground and background pair (FB-Pair) representation method, which consists of high- and low-response regions highlighted by the original CAM-generated online in the original image. During training, the original CAM is revised using the CAM generated by the FB-Pair. In addition, we design a self-supervised learning pretext task based on FB-Pair, which requires the model to predict whether the pixels in FB-Pair are from the original image during training. After this task, the model will accurately distinguish between different categories of objects.
Experiments on the thyroid nodule ultrasound image (TUI) data set revealed that our proposed method outperformed existing methods, with a 5.7% improvement in the mean intersection-over-union (mIoU) performance of segmentation compared with the second-best method and a reduction to 2.9% in the difference between the performance of benign and malignant nodules.
Our method trains a well-performing segmentation model on ultrasound images of thyroid nodules using only classification data. In addition, we determined that CAM can take full advantage of the information in the images to highlight the target regions more accurately and thus improve the segmentation performance.
Machine-to-machine (M2M) technology that allows machine devices to communicate directly with each other without human intervention has emerged as a cutting-edge technology for next-generation ...communication. As its applications become more and more popular, the number of users grows quickly and the quality of service needs to be improved. The traffic allocation problem may lead to many other problems such as low utilization ratio of the bandwidth and the jitter. When we tried to analyze the load on different paths using the simplest multipath routing algorithms, we found that the load changes just like simple harmonic motion, which inspires us to use physic and mathematic methods and tools to analyze the loading balance problems. And then, we designed a new traffic allocation algorithm. Compared with other algorithms, the algorithm proposed in this paper has much wider applicability. And the performance comparison experiment shows that DBTAs can really achieve improvement in decreasing the packet delay variance.
Knowledge graphs (KGs) are large-scale semantic networks designed to describe real-world facts. However, existing KGs typically contain only a small subset of all possible facts. Knowledge graph ...completion (KGC) is a task of inferring missing facts based on existing facts, which can help KGs become more complete. Tensor decomposition algorithms have proved promising for KGC problems. In this paper, we propose block decomposition based on relational interaction for knowledge graph completion (BDRI), a novel and robust model based on block term decomposition of the binary tensor representation of knowledge graph triples. Further, BDRI considers that the inverse relation, as one of the most important relation types, not only occupies a large proportion in real-world facts but also has an impact on other relation types. Although some existing models also take into account the importance of inverse relations, it is not enough to learn inverse relations independently. BDRI strengthens the fusion of forward relations and inverse relations by introducing inverse relations into the model in an enhanced way. We prove BDRI is full expressiveness and derive the bound on its entity and relation embedding dimensionality and smaller than the bound of SimplE and ComplEx. Experimental results on five public datasets show the effectiveness of BDRI.
Distantly Supervised Relation Extraction (DSRE) aligns existing knowledge bases with unstructured text to extract relation facts, and its automatically generated training data is inevitably noisy. ...Most existing works identify and reduce the impact of noise by enhancing semantic features. However, they only consider the semantic information in a single instance and ignore the semantic information between different instances. In this work, we propose a Semantic Piecewise Convolutional Neural Network (SPCNN), which uses the similarity between different entity pairs as semantic information to improve relation extraction. Specifically, to learn better semantic vector representations, we combine position features with entity pair features and entity similarity features in a high-dimensional space respectively, and generating two different semantic-aware representations. Then we unify these two representations to form a high-quality bag representation for training. Moreover, we design an Adaptive Negative Training (ANT) strategy, which facilitates the network to further exploit the rich semantic features to reduce the interference of noisy labels. Extensive experimental results on a large-scale benchmark dataset show that our method significantly outperforms other baselines.
Knowledge graphs (KGs) are large-scale semantic networks designed to describe real-world facts. Existing KGs contain only a fraction of what is really happening in the real life. Knowledge graph ...completion (KGC) has attracted attention because it can automatically infer and predict missing links in the KGs. The classical geometric, tensor decomposition and convolutional neural network (CNN) based models generate expressive feature embeddings, but these models treat triples independently and thus fail to cover the hidden information that is inherently implicit in the local neighborhood surrounding a triple. Recent works have introduced Graph Convolutional Network (GCN) into KGC task for leveraging the rich structural information in complex graphs. However, existing GCN-based models have limitations in relational topology distinction and multi-perspective feature aggregation. As multi-relational graphs, KGs display intrinsic heterogeneous structures and rich entity types. Therefore, ignoring the rich structural information and perspective features will greatly limit the expressive power of these models. In this paper, we propose multi-relational GCNs for modeling topological correlation and multi-perspective independence (CorIn). Specifically, we propose a multi-integration ring relational topology to fine-grained select neighbors according to relational correlation patterns, and capture the independence of multi-perspective feature groups by mutual information minimization. Our model adaptively utilizes an embedding learning design that can leverage a variety of entity-relation composition operations from classical KGC models. We evaluate our model on the public benchmark datasets and achieve marked performance gains in comparison to state-of-the-art methods.
Knowledge graph (KG) is becoming increasingly important in current information systems. To expand the coverage of KG, traditional knowledge graph completion research needs to collect enough training ...instances for newly added relations. However, high-quality training instances are usually difficult to collect. To alleviate this problem, knowledge graph zero-shot relational learning (KGZSL) has attracted more and more attention in recent years. The common method of KGZSL is to leverage Generative Adversarial Networks (GANs) to establish the connection between existing relation descriptions and the knowledge graph domain. However, traditional KGZSL methods often encounter training stability and model collapse problems, which means that these methods cannot stably generate high-quality relation vectors. Inspired by recent advances in prototype networks, we propose an end-to-end hybrid attention prototype framework to generate more plausible relational embeddings and address model collapse and training stability problems in previous studies. The core idea of our method is to obtain the relation prototype and the entity pair representation through the description encoder and the hybrid attention mechanism (HAM), then input them into a latent space, forcing the entity pair to be closer to their relation prototype. Experimental results on the knowledge graph zero-shot relational learning dataset demonstrate that our HAPZSL has a faster convergence speed and achieves state-of-the-art performance on this task.
PDF
