Low-Rank Adaptation (LoRA) enables parameter-efficient fine-tuning of Large Language Models (LLMs), and recent Mixture-of-Experts (MoE) extensions further enhance flexibility by dynamically combining multiple LoRA experts.However, existing MoE-augmented LoRA methods assume that experts operate independently, often leading to unstable routing, expert dominance.In this paper, we propose TalkLoRA, a communication-aware MoELoRA framework that relaxes this independence assumption by introducing expert-level communication prior to routing.TalkLoRA equips low-rank experts with a lightweight Talking Module that enables controlled information exchange across expert subspaces, producing a more robust global signal for routing.Theoretically, we show that expert communication smooths routing dynamics by mitigating perturbation amplification while strictly generalizing existing MoELoRA architectures.Empirically, TalkLoRA consistently outperforms vanilla LoRA and MoELoRA across diverse language understanding and generation tasks, achieving higher parameter efficiency and more balanced expert routing under comparable parameter budgets.These results highlight structured expert communication as a principled and effective enhancement for MoE-based parameterefficient adaptation.Code is available at https://github.com/why0129/TalkLoRA.

Bipartite graphs are widely used to model relationships between entities of different types, where vertices are divided into two disjoint sets. Biclique-preserving clustering is a fundamental operation that retrieves clusters with dense bicliques, enabling various emerging applications. However, existing methods either fail to accurately capture the unique properties of bipartite graphs or significantly overlook the informative higher-order biclique substructure, leading to compromised clustering quality. Additionally, existing methods are overly dependent on biclique enumeration, resulting in poor scalability. To address these challenges, we propose ECRC, a simple yet provable Edge-Centric Reweighting Clustering framework that provides strict approximation guarantees for any biclique. A key advantage of ECRC is its ability to leverage powerful counting instead of exhaustive enumeration, significantly reducing time and space complexity. To further improve efficiency, we propose several effective graph reduction strategies to eliminate the unqualified vertices and edges before calculating the edge-centric weight. Extensive experiments on five datasets show that our algorithms are more efficient and effective compared to six baselines.

Contrastive learning has demonstrated strong performance in attributed hypergraph clustering. Typically, existing methods based on contrastive learning first learn node embeddings and then apply clustering algorithms, such as k-means, to these embeddings to obtain the clustering results.However, these methods lack direct clustering supervision, risking the inclusion of clustering-irrelevant information in the learned graph. To this end, we propose a Contrastive learning approach for Attributed Hypergraph Clustering (CAHC), an end-to-end method that simultaneously learns node embeddings and obtains clustering results. CAHC consists of two main steps: representation learning and cluster assignment learning. The former employs a novel contrastive learning approach that incorporates both node-level and hyperedge-level objectives to generate node embeddings.The latter joint embedding and clustering optimization to refine these embeddings by clustering-oriented guidance and obtains clustering results simultaneously.Extensive experimental results demonstrate that CAHC outperforms baselines on eight datasets.

Existing community deception methods focus on perturbing edges to hide target communities, but they often overlook the unnoticeability of perturbations. Such neglect makes the attacks susceptible to anomaly detection. Therefore, we propose the “unnoticeable community deception” problem, which aims to hide the target community while requiring perturbations to be unnoticeable. To address this, we introduce local community deception based on comprehensive modularity (LCDC). Specifically, LCDC first constrains the perturbation scope to ensure newly added edges are indistinguishable from existing inter-community edges, thereby enhancing unnoticeability. LCDC uses only local information within the perturbation scope, without requiring access to the entire network. It then employs a perturbation cost to guide the selection of edges for addition or deletion. This cost is formulated as a weighted combination of comprehensive modularity and a node-level tendency to depart. Comprehensive modularity combines global and local components: global modularity ensures the overall network structure within the perturbation scope remains stable before and after perturbation, while local modularity aims to disperse nodes from the target community into other groups. LCDC only accesses the target community and its neighboring communities, not the entire network. Experimental results show that LCDC outperforms baseline methods in terms of unnoticeability and is competitive with them in terms of hiding effectiveness.

Most existing semi-supervised community detection algorithms leverage known communities to learn community structures, subsequently identifying communities that align with these learned community structures. However, differences in community structures may render the community structures learned by these methods inappropriate for the community containing the given node of interest. As a result, the identified community may exclude the given node or be of poor quality. Inspired by the success of reinforcement learning, we propose a Semi-supervised Local community detection method based on Reinforcement Learning, named SLRL, which only explores parts of the network surrounding the given node. It first extracts the local structure around a given node with an extractor, followed by selecting communities that are similar to this local structure to distill useful communities. These selected communities are employed to train the expander, which expands the community containing a given node. Experimental results demonstrate that SLRL outperforms state-of-the-art algorithms on five real-world datasets.

Low-rank adaptation (LoRA) has been developed as an efficient approach for adapting large language models (LLMs) by finetuning two low-rank matrices, thereby reducing the number of trainable parameters.However, prior research indicates that many of the weights in these matrices are redundant, leading to inefficiencies in parameter utilization.To address this limitation, we introduce Dense Low-Rank Adaptation (DenseLoRA), a novel approach that enhances parameter efficiency while achieving superior performance compared to LoRA.DenseLoRA builds upon the concept of representation fine-tuning, incorporating a single Encoder-Decoder to refine and compress hidden representations across all adaptation layers before applying adaptation.Instead of relying on two redundant low-rank matrices as in LoRA, DenseLoRA adapts LLMs through a dense low-rank matrix, improving parameter utilization and adaptation efficiency.We evaluate DenseLoRA on various benchmarks, showing that it achieves 83.8% accuracy with only 0.01% of trainable parameters, compared to LoRA's 80.8% accuracy with 0.70% of trainable parameters on LLaMA3-8B.Additionally, we conduct extensive experiments to systematically assess the impact of DenseLoRA's components on overall model performance.Code is available at https://github.com/mulin-ahu/DenseLoRA.

The information available in multi-attributed road-social networks includes network structure, location information, and numerical attributes. Most studies mainly focus on mining communities by combining structure with attributes or structure with location, which do not consider structure, attributes, and location simultaneously. Therefore, we propose a parameter-free algorithm, called LCDMRS, to mine local communities in multi-attributed road-social networks. LCDMRS extracts a sub-network surrounding the given node and embeds it to generate the vector representations of nodes, which incorporates both structural and attributed information. Based on the vector representations of nodes, the average cosine similarity between nodes is designed to ensure both the structural and attributed cohesiveness of the community, while the community node density is designed to ensure the spatial cohesiveness of the community. Targeting the community node density and cosine similarity of nodes, LCDMRS takes the given node as the starting node and employs the community dominance relation to expand the community outward. Experimental results on multiple real-world datasets demonstrate LCDMRS outperforms comparison algorithms.

Local spatial-aware community detection refers to detecting a spatial-aware community for a given node using local information. A spatial-aware community means that nodes in the community are tightly connected in structure, and their locations are close to each other. Existing studies focus on detecting the local non-overlapping spatial-aware community, i.e., detecting a spatial-aware community containing the given node. However, many geosocial networks often contain overlapping spatial-aware communities. Therefore, we propose a local overlapping spatial-aware community detection (LOSCD) problem, which aims to detect all spatial-aware communities that contain a given node with local information. To address LOSCD problem, we design an algorithm based on Spatial Modularity and Edge Similarity, called SMES. SMES contains two processes: spatial expansion and structure detection. The spatial expansion process involves using spatial modularity to identify nodes that are spatially close, while the structural detection process employs edge similarity to identify nodes that are structurally close. Experimental results demonstrate that SMES outperforms comparison algorithms in terms of both structural and spatial cohesiveness.

Individuals are often involved in multiple online social networks. Considering that owners of these networks are unwilling to share their networks, some global algorithms combine information from multiple networks to detect all communities in multiple networks without sharing their edges. When data owners are only interested in the community containing a given node, it is unnecessary and computationally expensive for multiple networks to interact with each other to mine all communities. Moreover, data owners who are specifically looking for a community typically prefer to provide less data than the global algorithms require. Therefore, we propose the Local Collaborative Community Detection problem (LCCD). It exploits information from multiple networks to jointly detect the local community containing a given node without directly sharing edges between networks. To address the LCCD problem, we present a method developed from M method, called colM, to detect the local community in multiple networks. This method adopts secure multiparty computation protocols to protect each network’s private information. Our experiments were conducted on real-world and synthetic datasets. Experimental results show that colM method could effectively identify community structures and outperform comparison algorithms.

Owing to the lack of a universal definition of communities, some semi-supervised community detection approaches learn the concept of community structures from known communities, and then dig out communities using learned concepts of communities. In some cases, users are only interested in the community containing a given node. However, communities detected by these semi-supervised approaches may not contain a given node. Besides, these methods traverse the entire network to detect many communities and cost more resources than a local algorithm. Therefore, it is necessary and meaningful to find the local community that contains a given node with prior information on the local network around the given node. We call this a Semi-supervised Local Community Detection (SLCD) problem. In this paper, prior information refers to certain known communities. To address the SLCD problem, we propose the Semi-supervised Local community detection with the Structural Similarity algorithm, called SLSS, which uses some known communities instead of all known communities. The idea of SLSS is to use the structural similarity between the known communities and the detected community, calculated by the graph kernel, to guide the expansion of the community. Experimental results show that SLSS outperforms other algorithms on six real-world datasets.

The identification of the local community structure in geo-social networks has been gaining increasing attention. The structure of geo-social networks evolves over time with the addition/deletion of edges/nodes and the update of node locations, which has motivated recent studies to mine local communities in dynamic geo-social networks. Mining communities in evolving geo-social networks is essential for understanding the evolution of group behaviors. However, in most previous studies on the community mining in dynamic networks, local spatial-aware communities were not identified in evolving geo-social networks. Therefore, in this study, the problem of determining local spatial-aware communities in evolving geo-social networks is proposed. To address this problem, we propose a parameter-free algorithm, called LSADEN. Specifically, LSADEN involves two main steps: i) selecting candidate nodes, where LSADEN defines the community dominance relation under dynamic environments to obtain candidate nodes that improve the community in terms of the community quality or the smoothness between communities at adjacent time stamps; ii) community expansion, where LSADEN designs the Manhattan distance of communities to add some candidate nodes to the local community. Experimental results on six real-world datasets and one synthetic dataset show that LSADEN performs well both in terms of the quality of communities and the smoothness between communities at adjacent time stamps.

The problem of finding the spatial-aware community for a given node has been defined and investigated in geosocial networks. However, existing studies suffer from two limitations: 1) the criteria of defining communities are determined by parameters, which are difficult to set, and 2) algorithms may require global information and are not suitable for situations where the network is incomplete. Therefore, we propose spatial-aware local community detection (SLCD), which finds the spatial-aware local community with only local information and defines the community based on the difference in terms of the sparseness of edges inside and outside the community. Specifically, to address the SLCD problem, we design a novel spatial aware local community detection algorithm based on dominance relation, but this algorithm incurs high cost. To further improve the efficiency, we propose a greedy algorithm. Experimental results demonstrate that the proposed greedy algorithm outperforms the comparison algorithms.

In real-world applications, each data owner might have only partial information of the complete social networks. They wish to find the community structure within multiple networks but without sharing their data directly. However, the existing works on collaborative community detection rarely consider the edges privacy issue in the networks. In this article, from the view of secure multiparty computation, we present two methods to detect the community structure of the multiple networks without directly exchanging edges’ information. These two methods are developed from the fast modularity algorithm ($fastModular$) and the label propagation algorithm (LPA), and they are called$CofastModular$and$CoLPA$, respectively. Both methods can detect the community structure within multiple networks without the need to directly exchange the edges’ information. Experiments are conducted on several real-world and synthetic networks. Experimental results show that$CofastModular$and$CoLPA$could identify community structure effectively.

Although followership has been widely studied in sociology and management, the problem of finding followers has not drawn attention in the field of artificial intelligence. We refer to the problem of finding followers of a given object as followers search. In sociology, followers are close to their leaders, and leaders are superior to their followers. In this article, aimed at finding followers of a given object, we formulate followers on the basis of both superiority and closeness. The former means that the given object should be superior to followers, and the latter means that followers should be close to the given object. We present a followers search algorithm to find the followers of the given object. Furthermore, we apply the ideas of followers to the market basket and recommender system datasets. The experimental results demonstrate the rationality of the discovered followers on the market basket dataset and the improved performance of the TrustPMF algorithm by adopting followership on recommender system datasets, which indicate a promising future for followers search.

In real-world social networks, global information (e.g., the number of nodes and the connections between them) is incomplete or expensive to acquire; therefore, local community detection becomes especially important. Local community detection is used to identify the local community to which the given starting node belongs according to local information. For a given node, most existing local community detection methods can only find single scale local communities but not those of variable sizes. However, local communities with different scales are often required. Therefore, it is necessary and meaningful to find local communities of the given starting node with different scales; we call this multiscale local community detection. In this paper, we propose a new local modularity inspired by the global modularity and prove the equivalence of the proposed local modularity with two other typical local modularities. Furthermore, to detect local communities with different scales, we present a method based on the proposed local modularity. We test this method on several synthetic and real datasets, and the experimental results indicate that the detected community is meaningful and its scale can be changed reasonably.

Dynamic social networking has always been the focus of the social network research, and a large number of effective community detection algorithms have been developed. However, as the real social networks are difficult to access, it is also difficult to evaluate the effectiveness of the community detection algorithms on dynamic social networks. Existing dynamic social network generators only focus on edge or node changes, whereas the quality of the community structure (modularity) is not considered. We propose a time-evolving social network generator based on modularity (TESNG-M). In TESNG-M, according to the community partition of the original network, the evolutionary behavior is simulated by adding or deleting nodes and flipping edges so that a static social network with a specified modularity will be generated. By repeating the static generation process, we obtain a dynamic social network with a specified partition and modularity at each time step. Thus, the network generated by TESNG-M can effectively simulate a real dynamic social network and be used for community detection. Furthermore, the specified modularity of static synthetic networks and the dynamic modularity of dynamic synthetic networks could be regarded as the performance baseline of community detection algorithms in static and dynamic social networks, respectively.

Local community detection refers to finding the community that contains the given node based on local information, which becomes very meaningful when global information about the network is unavailable or expensive to acquire. Most studies on local community detection focus on finding non-overlapping communities. However, many real-world networks contain overlapping communities like social networks. Given an overlapping node that belongs to multiple communities, the problem is to find communities to which it belongs according to local information. We propose a framework for local overlapping community detection. The framework has three steps. First, find nodes in multiple communities to which the given node belongs. Second, select representative nodes from nodes obtained above, which tends to be in different communities. Third, discover the communities to which these representative nodes belong. In addition, to demonstrate the effectiveness of the framework, we implement six versions of this framework. Experimental results demonstrate that the six implementation versions outperform the other algorithms.

Most of the community detection methods require the global information of the original network to be available, however, it is often expensive (even no way) to obtain the global information of the network in many real-world networks. So, the local community detection, only based on the local information, becomes especially important. The local community is the community in the network to which a given starting node belongs. Some local community detection methods have been proposed. However, these methods did not consider the characteristics of the local community during the local community formation. In this paper, we analyze the formation of the local community and propose two local community detection algorithms based on the dynamic membership function. Each of the algorithms is divided into three stages: 1) the initial stage, 2) the middle stage, and 3) the closing stage. At the initial stage, we design a dynamical membership function to detect local community and nodes with the greatest neighborhood intersect rate could be added to the local community. At the middle stage, we design another dynamical membership function, and the goal of this stage is to make the connection of the node in the local community closest. At the closing stage, the third dynamical membership function is provided, and the local community is further improved by collecting some nodes that should not be omitted. We test our algorithms on several synthetic datasets and real datasets; the results show that the local communities detected by our method are closer to the real local communities.

Clustering is a classical unsupervised learning task, which is aimed to divide a data set into several groups with similar objects. Clustering problem has been studied for many years, and many excellent clustering algorithms have been proposed. In this paper, we propose a novel clustering method based on density, which is simple but effective. The primary idea of the proposed method is given as follows. Firstly, the point with the largest local density in a cluster is considered as the cluster center. The local density of each point is estimated based on the distance (called radius) between the point and its k-th nearest neighbor. The point with a smaller radius indicates a larger local density. Secondly, the difference of the local densities between each two internal points should be small, while the difference between the density of a border point and the density of an internal point should be relatively large. Thirdly, if the intersection of k nearest neighbors of two points is small, they should be assigned to different clusters. The proposed algorithm has been compared with a typical clustering algorithm named FDPCluster, and the experimental results show that our algorithm has better clustering quality.