Zero-shot stance detection aims to identify the stance expressed in social media text aimed at specific targets without relying on annotated data. However, due to insufficient contextual information and the inherent ambiguity of language, this task faces numerous challenges in low-resource scenarios. This work proposes a novel zero-shot stance detection method based on multi-agent debate (ZSMD) to address the aforementioned challenges. Specifically, we construct two debater agents representing the supporting and opposing stances. A knowledge enhancement module supplements the original tweet and target with relevant background knowledge, providing richer contextual support for argument generation. Subsequently, the two agents engage in debate over a predetermined number of rounds, employing rebuttal strategies such as factual verification, logical analysis, and sentiment analysis. If no consensus is reached within the specified rounds, a referee agent synthesizes the debate process and original input information to deliver the final stance determination. We evaluate ZSMD on two benchmark datasets, SemEval-2016 Task 6 and P-Stance, and compare it against strong zero-shot baselines such as MB-Cal and COLA. The experimental results show that ZSMD not only achieves higher accuracy than these baselines, but also provides deeper insights into subtle differences in opinion expression, highlighting the potential of structured argumentation in low-resource settings.

This paper presents a twisting controller (TC) based on a high-order sliding mode observer (HOSMO) for linear induction motors (LIMs), accounting for dynamic end effects. Based on the LIM model in the field-oriented frame, two extended subsystems are developed: a velocity extended model and a flux extended model. Using these models, two HOSMOs are designed to estimate the disturbances in each subsystem. The HOSMO outputs are then used for disturbance rejection, resulting in two second-order systems with small bounded disturbances. Two TCs are subsequently implemented to achieve finite-time velocity and flux tracking of the LIM. The primary advantage of this strategy lies in its ability to reduce chattering through active disturbance rejection. Hardware-in-the-loop (HIL) experiments validate the effectiveness of the proposed TC-HOSMO scheme.

The Dynamic Multi-objective Optimization Problem (DMOP) is one of the common problem types in academia and industry. The Dynamic Multi-Objective Evolutionary Algorithm (DMOEA) is an effective way for solving DMOPs. Despite the existence of many research works proposing a variety of DMOEAs, the demand for efficient solutions to DMOPs in drastically changing scenarios is still not well met. To this end, this paper is oriented towards DMOEA and innovatively proposes to explore the correlation between different points of the optimal frontier (PF) to improve the accuracy of predicting new PFs for new environments, which is the first attempt, to our best knowledge. Specifically, when the DMOP environment changes, this paper first constructs a spatio-temporal correlation model between various key points of the PF based on the linear regression algorithm; then, based on the constructed model, predicts a new location for each key point in the new environment; subsequently, constructs a sub-population by introducing the Gaussian noise into the predicted location to improve the generalization ability; and then, utilizes the idea of NSGA-II-B to construct another sub-population to further improve the population diversity; finally, combining the previous two sub-populations, re-initializing a new population to adapt to the new environment through a random replacement strategy. The proposed method was evaluated by experiments on the CEC 2018 test suite, and the experimental results show that the proposed method can obtain the optimal MIGD value on six DMOPs and the optimal MHVD value on five DMOPs, compared with six recent research results.

Owing to the heterogeneity and incomplete information present in various domain knowledge graphs, the alignment of distinct source entities that represent an identical real-world entity becomes imperative. Existing methods focus on cross-lingual knowledge graph alignment, and assume that the entities of knowledge graphs in the same language are unique. However, due to the ambiguity of language, heterogeneous knowledge graphs in the same language are often duplicated, and relationship triples are far less than those of cross-lingual knowledge graphs. Moreover, existing methods rarely exclude noisy entities in the process of alignment. These make it impossible for existing methods to deal effectively with the entity alignment of domain knowledge graphs. In order to address these issues, we propose a novel entity alignment approach based on domain-oriented embedded representation (DomainEA). Firstly, a filtering mechanism employs the language model to extract the semantic features of entities and to exclude noisy entities for each entity. Secondly, a Structural Aggregator (SA) incorporates multiple hidden layers to generate high-order neighborhood-aware embeddings of entities that have few relationship connections. An Attribute Aggregator (AA) introduces self-attention to dynamically calculate weights that represent the importance of the attribute values of the entities. Finally, the approach calculates a transformation matrix to map the embeddings of distinct domain knowledge graphs onto a unified space, and matches entities via the joint embeddings of the SA and AA. Compared to six state-of-the-art methods, our experimental results on multiple food datasets show the following: (i) Our approach achieves an average improvement of 6.9% on MRR. (ii) The size of the dataset has a subtle influence on our approach; there is a positive correlation between the expansion of the dataset size and an improvement in most of the metrics. (iii) We can achieve a significant improvement in the level of recall by employing a filtering mechanism that is limited to the top-100 nearest entities as the candidate pairs.

Imbalanced node classification is an important research topic in graph learning. With the rise of deep learning, powerful models like graph neural networks (GNNs) have been widely used in node classification tasks and achieved promising performance. However, real-world graphs are usually imbalanced, characterized by some classes having an adequate amount of data while others lack data. This imbalance presents the suboptimal classification performance of the model. Therefore, research on the GNNs-based imbalanced node classification is crucial. This article aims to systematically summarize the development status of GNNs in imbalanced node classification. First, the related concepts of GNNs and imbalanced node classification are introduced to establish a solid foundation for readers. Second, the methods are divided into data-level methods and algorithm-level methods, then subdivided into seven subcategories. Especially, we discuss the key thoughts, relative strengths, and weaknesses of classic methods in each subcategory. Then, datasets and common evaluation metrics are compiled to provide a wealth of useful resources. Finally, future research directions for imbalanced node classification on graphs are introduced to promote the boom of this field.