Traditional recommenders often fail to disentangle the motivations behind user choices. To address this, we propose MV-LLMRec, a framework that models interactions through three views: Structural, Intent, and Conformity. MV-LLMRec leverages LLMs to generate rich semantic representations for intent and conformity, which are refined through graph propagation and dynamically fused via an attention mechanism. We evaluate MV-LLMRec on the Amazon-Movie and Amazon-Book datasets and show that it significantly outperforms state-of-the-art baselines, validating our approach.

Large Language Models (LLMs) extended to multi-modal inputs have led to Multi-modal LLMs (MLLMs) that perform strongly on vision-language tasks. Recent MLLMs adopt multi-resolution inputs to capture both global context and local details, but this substantially increases visual tokens and computational cost. Existing pruning methods reduce redundancy but are designed for single-resolution settings, overlooking the characteristics of multi-resolution tokens. We observe two key properties: tokens from different resolutions follow distinct distributions of information content, and tokens across resolutions exhibit mutual complementarity, such that pruning one type can often be compensated by the other. Based on this observation, we propose Multi-Resolution Token Pruning method (MR-Pruner), a training-free, graph-based pruning framework for multi-resolution MLLMs. MR-Pruner incorporates three components—Intra-resolution, Cross-resolution Token Scoring, and Informativeness-aware Token Pruning—that adaptively allocate pruning ratios and facilitate information propagation across resolutions. Experiments on eight benchmarks show that MR-Pruner achieves superior efficiency–performance trade-offs. For example, when only 10% of the visual tokens are retained, it leads to an average performance degradation of 3.6%. For reproducibility, the source code is available at https://github.com/gooriiie/MR-Pruner.

Recent advances in large language models (LLMs), such as GPT and Llama, have driven significant progress in natural language processing and diverse AI applications. In this paper, we explore how LLMs can enhance the construction of heterogeneous citation networks by integrating rich contextual information derived from LLMs. We propose a metadata-driven augmentation that generates concise factual descriptions for sparse fields in citation metadata, including keywords, venues, and author affiliations. These contexts are encoded with DeBERTa and integrated as node features in a knowledge-enriched heterogeneous network. Additionally, to mitigate LLM hallucinations, we employed Chain-of-Thought (CoT)-based prompting and evaluated the quality of the generated context. Experimental results demonstrate that our LLM-powered context augmentation improves author classification by 2.0%-4.5% and author clustering by 8.9%-18.1%, outperforming traditional feature engineering methods. The dataset and source code are available at https://github.com/inthwan/Metadata-Meets-LLMs.

Community detection in signed networks is challenging due to the presence of both positive and negative edges, which violate the homophily assumption commonly used in traditional methods. In this paper, we present CR-SGCN, an unsupervised framework for community detection in signed networks. It combines a signed GCN encoder, a soft community assignment layer, and a degree-corrected stochastic block model decoder. To enhance boundary separation, we introduce an edge-level signed conductance regularization that pulls intra-community embeddings closer and pushes inter-community ones apart. Without requiring labels, CR-SGCN effectively captures community structure even under edge sparsity. Experiments on real-world signed networks show consistent gains in signed modularity and structural separation over existing baselines. The results demonstrate the robustness and effectiveness of CR-SGCN for unsupervised signed community detection.

Graph Neural Networks (GNNs) excel at learning from structured data, yet fairness in regression tasks remains underexplored. Existing approaches mainly target classification and representation-level debiasing, which cannot fully address the continuous nature of node-level regression. We propose FnRGNN, a fairness-aware in-processing framework for GNN-based node regression that applies interventions at three levels: (i) structure-level edge reweighting, (ii) representation-level alignment via MMD, and (iii) prediction-level normalization through Sinkhorn-based distribution matching. This multi-level strategy ensures robust fairness under complex graph topologies. Experiments on four real-world datasets demonstrate that FnRGNN reduces group disparities without sacrificing performance. Code is available at https://github.com/sybeam27/FnRGNN.

To leverage the complex structures within heterogeneous graphs, recent studies on heterogeneous graph embedding use a hyperbolic space, characterized by a constant negative curvature and exponentially increasing space, which aligns with the structural properties of heterogeneous graphs. However, despite heterogeneous graphs inherently possessing diverse power-law structures, most hyperbolic heterogeneous graph embedding models use a single hyperbolic space for the entire heterogeneous graph, which may not effectively capture the diverse power-law structures within the heterogeneous graph. To address this limitation, we propose Multi-hyperbolic Space-based heterogeneous Graph Attention Network (MSGAT), which uses multiple hyperbolic spaces to effectively capture diverse power-law structures within heterogeneous graphs. We conduct comprehensive experiments to evaluate the effectiveness of MSGAT. The experimental results demonstrate that MSGAT outperforms state-of-the-art baselines in various graph machine learning tasks, effectively capturing the complex structures of heterogeneous graphs.

In recent years, many recommender systems using network embedding (NE) such as graph neural networks (GNNs) have been extensively studied in the sense of improving recommendation accuracy. However, such attempts have focused mostly on utilizing only the information of positive user-item interactions with high ratings. Thus, there is a challenge on how to make use of low rating scores for representing users' preferences since low ratings can be still informative in designing NE-based recommender systems. In this study, we present SiReN, a new Si gn-aware Recommender system based on GNN models. Specifically, SiReN has three key components: 1) constructing a signed bipartite graph for more precisely representing users' preferences, which is split into two edge-disjoint graphs with positive and negative edges each; 2) generating two embeddings for the partitioned graphs with positive and negative edges via a GNN model and a multilayer perceptron (MLP), respectively, and then using an attention model to obtain the final embeddings; and 3) establishing a sign-aware Bayesian personalized ranking (BPR) loss function in the process of optimization. Through comprehensive experiments, we empirically demonstrate that SiReN consistently outperforms state-of-the-art NE-aided recommendation methods.

Traffic forecasting is a crucial application of the Intelligent Transportation System (ITS), with research focusing on various methods, from classical statistical approaches to graph-based methods integrated with RNN-based approaches to capture spatial and temporal correlations simultaneously. During the traffic data collection phase, the absence of vehicles on each road or sensor malfunctions can result in the collection of traffic time series data as zeros. However, storing such zero values makes accurate traffic prediction more challenging. To address this challenge, we present a novel model for improving traffic forecasting using graph convolutional recurrent neural networks. The proposed method is evaluated on two real-world public benchmark datasets and compared with six baseline models, showcasing its superior performance.

We present five approaches for interpolating missing data in real-world traffic datasets using basic, statistical, and generative model methods. The effectiveness of these approaches is evaluated using graph deep learning models, and the results show that imputing missing data improves the performance of traffic prediction models, especially when dealing with a higher proportion of missing data. The experiments are conducted on two real-world datasets, METR-LA and PEMS-BAY, to evaluate the proposed methods comprehensively. The results demonstrate that imputing missing data significantly enhances the performance of traffic prediction models, particularly when dealing with a higher proportion of missing data.

Identifying cohesive subgraphs in hypergraphs is a fundamental problem that has received recent attention in data mining and engineering fields. Existing approaches mainly focus on a strongly induced subhypergraph or edge cardinality, overlooking the importance of the frequency of co-occurrence. In this paper, we propose a new cohesive subgraph named (k,g)-core, which considers both neighbour and co-occurrence simultaneously. The (k,g)-core has various applications including recommendation system, network analysis, and fraud detection. To the best of our knowledge, this is the first work to combine these factors. We extend an existing efficient algorithm to find solutions for (k,g)-core. Finally, we conduct extensive experimental studies that demonstrate the efficiency and effectiveness of our proposed algorithm.

Approximate Policy Iteration (API) algorithms alternate between (approximate) policy evaluation and (approximate) greedification. Many different approaches have been explored for approximate policy evaluation, but less is understood about approximate greedification and what choices guarantee policy improvement. In this work, we investigate approximate greedification when reducing the KL divergence between the parameterized policy and the Boltzmann distribution over action values. In particular, we investigate the difference between the forward and reverse KL divergences, with varying degrees of entropy regularization; these are chosen because they underlie many existing policy optimization approaches, as we highlight in this work. We show that the reverse KL has stronger policy improvement guarantees, and that reducing the forward KL can result in a worse policy. We also demonstrate, however, that a large enough reduction of the forward KL can induce improvement under additional assumptions. Empirically, we show on simple continuous-action environments that the forward KL can induce more exploration, but at the cost of a more suboptimal policy. No significant differences were observed in the discrete-action setting or on a suite of benchmark problems. This work provides novel theoretical and empirical insights about the forward KL and reverse KL for greedification, and clear next steps for understanding and improving our policy optimization algorithms.

Learning latent representations in graphs is finding a mapping that embeds nodes or edges as data points in a low-dimensional vector space. This paper introduces a flexible framework to enhance existing methodologies that have difficulty capturing local proximity and global relationships at the same time. Our approach generates a virtual edge between non-adjacent nodes based on the Forman-Ricci curvature in network. By analyzing the network using topological information, global relationships structurally similar can easily be detected and successfully integrated with previous works.

Given a graph G and the desired size k in bits, how can we summarize G within k bits, while minimizing the information loss?

This paper proposes LinkBlackHole*, a novel algorithm for finding communities that are (i) overlapping in nodes and (ii) mixing (not separating clearly) in links. There has been a small body of work in each category, but this paper is the first one that addresses both. For this purpose, LinkBlackHole* incorporates the advantages of both the link-space transformation and the black hole transformation. Thorough experiments show superior quality of the communities detected by LinkBlackHole* to those detected by other state-of-the-art algorithms.

This paper proposes LinkBlackHole*, a novel algorithm for finding communities that are (i) overlapping in nodes and (ii) mixing (not separating clearly) in links. There has been a small body of work in each category, but this paper is the first one that addresses both. LinkBlackHole* is a merger of our earlier two algorithms, LinkSCAN* and BlackHole, inheriting their advantages in support of highly-mixed overlapping communities. The former is used to handle overlapping nodes, and the latter to handle mixing links in finding communities. Like LinkSCAN and its more efficient variant LinkSCAN*, this paper presents LinkBlackHole and its more efficient variant LinkBlackHole*, which reduces the number of links through random sampling. Thorough experiments show superior quality of the communities detected by LinkBlackHole* and LinkBlackHole to those detected by other state-of-the-art algorithms. In addition, LinkBlackHole* shows high resilience to the link sampling effect, and its running time scales up almost linearly with the number of links in a network.

Amulti-layer graphconsists of multiple layers of weighted graphs, where the multiple layers represent the different aspects of relationships. Considering multiple aspects (i.e., layers) together is essential to achieve a comprehensive and consolidated view. In this article, we propose a novel framework ofdifferential flattening, which facilitates the analysis of multi-layer graphs, and apply this framework to community detection. Differential flattening merges multiple graphs into a single graph such that the graph structure with the maximum clustering coefficient is obtained from the single graph. It has two distinct features compared with existing approaches. First, dealing with multiple layers is doneindependentlyof a specific community detection algorithm, whereas previous approaches rely on a specific algorithm. Thus, any algorithm for a single graph becomes applicable to multi-layer graphs. Second, the contribution of each layer to the single graph is determinedautomaticallyfor the maximum clustering coefficient. Since differential flattening is formulated by an optimization problem, the optimal solution is easily obtained by well-known algorithms such as interior point methods. Extensive experiments were conducted using the Lancichinetti-Fortunato-Radicchi (LFR) benchmark networks as well as the DBLP, 20 Newsgroups, and MIT Reality Mining networks. The results show that our approach of differential flattening leads to discovery of higher-quality communities than baseline approaches and the state-of-the-art algorithms.

With regard to social network analysis, we concentrate on two widely-accepted building blocks: community detection and graph drawing. Although community detection and graph drawing have been studied separately, they have a great commonality, which means that it is possible to advance one field using the techniques of the other. In this paper, we propose a novel community detection algorithm for undirected graphs, called BlackHole, by importing a geometric embedding technique from graph drawing. Our proposed algorithm transforms the vertices of a graph to a set of points on a low-dimensional space whose coordinates are determined by a variant of graph drawing algorithms, following the overall procedure of spectral clustering. The set of points are then clustered using a conventional clustering algorithm to form communities. Our primary contribution is to prove that a common idea in graph drawing, which is characterized by consideration of repulsive forces in addition to attractive forces, improves the clusterability of an embedding. As a result, our algorithm has the advantages of being robust especially when the community structure is not easily detectable. Through extensive experiments, we have shown that BlackHole achieves the accuracy higher than or comparable to the state-of-the-art algorithms.

In this paper, for overlapping community detection, we propose a novel framework of the link-space transformation that transforms a given original graph into a link-space graph. Its unique idea is to consider topological structure and link similarity separately using two distinct types of graphs: the line graph and the original graph. For topological structure, each link of the original graph is mapped to a node of the link-space graph, which enables us to discover overlapping communities using non-overlapping community detection algorithms as in the line graph. For link similarity, it is calculated on the original graph and carried over into the link-space graph, which enables us to keep the original structure on the transformed graph. Thus, our transformation, by combining these two advantages, facilitates overlapping community detection as well as improves the resulting quality. Based on this framework, we develop the algorithm LinkSCAN that performs structural clustering on the link-space graph. Moreover, we propose the algorithm LinkSCAN* that enhances the efficiency of LinkSCAN by sampling. Extensive experiments were conducted using the LFR benchmark networks as well as some real-world networks. The results show that our algorithms achieve higher accuracy, quality, and coverage than the state-of-the-art algorithms.

In this paper, we consider the Max-Weight protocol for routing and scheduling in wireless networks under an adversarial model. This protocol has received a significant amount of attention dating back to the papers of Tassiulas and Ephremides. In particular, this protocol is known to be throughput-optimal whenever the traffic patterns and propagation conditions are governed by a stationary stochastic process. However, the standard proof of throughput optimality (which is based on the negative drift of a quadratic potential function) does not hold when the traffic patterns and the edge capacity changes over time are governed by an arbitrary adversarial process. Such an environment appears frequently in many practical wireless scenarios when the assumption that channel conditions are governed by a stationary stochastic process does not readily apply. In this paper, we prove that even in the above adversarial setting, the Max-Weight protocol keeps the queues in the network stable (i.e., keeps the queue sizes bounded) whenever this is feasible by some routing and scheduling algorithm. However, the proof is somewhat more complex than the negative potential drift argument that applied in the stationary case. Our proof holds for any arbitrary interference relationships among edges. We also prove the same stability of ε-approximate Max-Weight under the adversarial model. We conclude the paper with a discussion of queue sizes in the adversarial model as well as a set of simulation results.

In this paper we consider the MAX-WEIGHT protocol for routing and scheduling in wireless networks under an adversarial model. This protocol has received a significant amount of attention dating back to the papers of Tassiulas and Ephremides. In particular, this protocol is known to be throughput-optimal whenever the traffic patterns and propagation conditions are governed by a stationary stochastic process. However, the standard proof of throughput optimality (which is based on the negative drift of a quadratic potential function) does not hold when the traffic patterns and the edge capacity changes over time are governed by an arbitrary adversarial process. Such an environment appears frequently in many practical wireless scenarios when the assumption that channel conditions are governed by a stationary stochastic process does not readily apply. In this paper we prove that even in the above adversarial setting, the MAX-WEIGHT protocol keeps the queues in the network stable (i.e. keeps the queue sizes bounded) whenever this is feasible by some routing and scheduling algorithm. However, the proof is somewhat more complex than the negative potential drift argument that applied in the stationary case. Our proof holds for any arbitrary interference relationships among edges. We also prove the stability of ε-approximate MAX-WEIGHT under the adversarial model. We conclude the paper with a discussion of queue sizes in the adversarial model as well as a set of simulation results.