While retrieval-augmented generation systems partially address the hallucination issues in large language models, it also introduces new vulnerabilities to knowledge corruption attacks. Adversaries exploit these vulnerabilities by poisoning documents provided by RAG system to manipulate LLM outputs. To counter this threat, we propose SecureCollaRAG, a Byzantine-tolerant collaborative RAG framework leveraging Multi-source Knowledge Validation Mechanism. Our approach enables agent system to securely verify document provenance through dynamic GNN-based credibility scoring, effectively preventing stealthy knowledge corruption attacks while preserving essential domain knowledge integrity. Through extensive evaluations and formal analysis, we demonstrate that SecureCollaRAG maintains robustness against attackers under non-IID data distributions.

Ensuring character identity consistency across varying prompts remains a fundamental limitation in diffusion-based text-to-image generation. We propose CharCom, a modular and parameter-efficient framework that achieves character-consistent story illustration through composable LoRA adapters, enabling efficient per-character customization without retraining the base model. Built on a frozen diffusion backbone, CharCom dynamically composes adapters at inference using prompt-aware control. Experiments on multi-scene narratives demonstrate that CharCom significantly enhances character fidelity, semantic alignment, and temporal coherence. It remains robust in crowded scenes and enables scalable multi-character generation with minimal overhead, making it well-suited for real-world applications such as story illustration and animation.

Dynamic networks are data structures that represent the interactions among various entities in real-world systems, with their topology and node properties evolving over time. However, prevailing approaches typically derive node embeddings through aggregating temporal neighbor nodes of adjacent several hops, thus failing to capture the long temporal dependencies in dynamic networks. Furthermore, existing research on dynamic networks focuses on node- and edge-level tasks, lacking the support of graph-level tasks. To address the limitations of current approaches, this paper proposes TP-GNN, a novel continuous dynamic graph neural network model intended for graph classification in dynamic networks, which offers two primary advantages: (1) TP-GNN captures the long temporal dependencies via a novel message-passing method based on the information flow among the nodes, and (2) it learns the network evolution process from edge order for accurate dynamic network analytics. We evaluate the performance of TP-GNN in five datasets, including a new dataset we created from a Java software project. The results show that our method outperforms state-of-the-art approaches in graph classification with an average improvement of 4.91% in terms of$F_{1}$Score11Codes and dataset are available at https://github.com/Jie-0828/TP-GNN..

This paper presents a novel perspective on the relationship between decentralization, a prevalent characteristic of multi-agent systems, and centralization, which involves imposing central control to achieve system-level objectives. Specifically, within the context of a networked opinion dynamic model, we introduce and discuss a framework for centralization. In this framework, a decentralized network consists of autonomous agents and a dynamic, unknown social structure. Centralization involves appointing specific agents in the network as access units, responsible for providing information and exerting influence within their local environments. We focus on centralization for the DeGroot model of opinion dynamics, aiming to achieve opinion convergence with the minimum number of access units. To accomplish this, we demonstrate that selecting access units to form a dominating set is crucial. Moreover, we propose algorithms based on a new local algorithmic framework called prowling to facilitate this process. Through systematic experiments conducted on both real-world and synthetic networks, we validate our algorithm and show its superiority over benchmark methods.

This paper is the first to use contrastive learning to improve the robustness of graph representation learning for signed bipartite graphs, which are commonly found in social networks, recommender systems, and paper review platforms. Existing contrastive learning methods for signed graphs cannot capture implicit relations between nodes of the same type in signed bipartite graphs, which have two types of nodes and edges only connect nodes of different types. We propose a Signed Bipartite Graph Contrastive Learning (SBGCL) method to learn robust node representation while retaining the implicit relations between nodes of the same type. SBGCL augments a signed bipartite graph with a novel two-level graph augmentation method. At the top level, we maintain two perspectives of the signed bipartite graph, one presents the original interactions between nodes of different types, and the other presents the implicit relations between nodes of the same type. At the bottom level, we employ stochastic perturbation strategies to create two perturbed graphs in each perspective. Then, we construct positive and negative samples from the perturbed graphs and design a multi-perspective contrastive loss to unify the node presentations learned from the two perspectives. Results show proposed model is effective over state-of-the-art methods on real-world datasets.

Signed graphs model complex relations using both positive and negative edges. Signed graph neural networks (SGNN) are powerful tools to analyze signed graphs. We address the vulnerability of SGNN to potential edge noise in the input graph. Our goal is to strengthen existing SGNN allowing them to withstand edge noises by extracting robust representations for signed graphs. First, we analyze the expressiveness of SGNN using an extended Weisfeiler-Lehman (WL) graph isomorphism test and identify the limitations to SGNN over triangles that are unbalanced. Then, we design some structure-based regularizers to be used in conjunction with an SGNN that highlight intrinsic properties of a signed graph. The tools and insights above allow us to propose a novel framework, Robust Signed Graph Neural Network (RSGNN), which adopts a dual architecture that simultaneously denoises the graph while learning node representations. We validate the performance of our model empirically on four real-world signed graph datasets, i.e., Bitcoin_OTC, Bitcoin_Alpha, Epinion and Slashdot, RSGNN can clearly improve the robustness of popular SGNN models. When the signed graphs are affected by random noise, our method outperforms baselines by up to 9.35% Binary-F1 for link sign prediction. Our implementation is available in PyTorch1.

Next POI recommendation intends to forecast users' immediate future movements given their current status and historical information, yielding great values for both users and service providers. However, this problem is perceptibly complex because various data trends need to be considered together. This includes the spatial locations, temporal contexts, user's preferences, etc. Most existing studies view the next POI recommendation as a sequence prediction problem while omitting the collaborative signals from other users. Instead, we propose a user-agnostic global trajectory flow map and a novel Graph Enhanced Transformer model (GETNext) to better exploit the extensive collaborative signals for a more accurate next POI prediction, and alleviate the cold start problem in the meantime. GETNext incorporates the global transition patterns, user's general preference, spatio-temporal context, and time-aware category embeddings together into a transformer model to make the prediction of user's future moves. With this design, our model outperforms the state-of-the-art methods with a large margin and also sheds light on the cold start challenges within the spatio-temporal involved recommendation problems.

Traffic flow forecasting is a crucial task in urban computing. The challenge arises as traffic flows often exhibit intrinsic and latent spatio-temporal correlations that cannot be identified by extracting the spatial and temporal patterns of traffic data separately. We argue that such correlations are universal and play a pivotal role in traffic flow. We put forward spacetime interval learning as a paradigm to explicitly capture these correlations through a unified analysis of both spatial and temporal features. Unlike the state-of-the-art methods, which are restricted to a particular road network, we model the universal spatio-temporal correlations that are transferable from cities to cities. To this end, we propose a new spacetime interval learning framework that constructs a local-spacetime context of a traffic sensor comprising the data from its neighbors within close time points. Based on this idea, we introduce local spacetime neural network (STNN), which employs novel spacetime convolution and attention mechanism to learn the universal spatio-temporal correlations. The proposed STNN captures local traffic patterns, which does not depend on a specific network structure. As a result, a trained STNN model can be applied on any unseen traffic networks. We evaluate the proposed STNN on two public real-world traffic datasets and a simulated dataset on dynamic networks. The experiment results show that STNN not only improves prediction accuracy by 15% over state-of-the-art methods, but is also effective in handling the case when the traffic network undergoes dynamic changes as well as the superior generalization capability.

Prominent structural patterns such as small-world and core-periphery structures amount to some of the most important emergent characteristics of a social network. Yet little work is done to interpret these emergent phenomena in a unified way. Towards a unified interpretation framework, we connect the establishment of social patterns with social capital. Social capital captures the benefits that an individual gains from its social surrounding. We argue that individuals' desire to gaining higher social capital may give rise to important network properties. To validate this claim, we propose social capital game that mathematically conceptualizes bonding and bridging social capital. This framework allows us to regard individuals in a social network as learning agents who gain social capital through iteratively building interpersonal ties. The link-building decisions of these agents are guided by a multiagent reinforcement learning (MARL) algorithm which improves agents' capability through repeated game plays. We conduct a series of experiments which demonstrate (1) the collective behaviors of the agents give rise to salient social patterns, and (2) by varying agents' preferences to different forms of social capital, different types of social patterns emerge. In particular, bonding social capital plays a pivotal role in the formation of a community structure in the network while bridging social capital is instrumental to the emergence of core-periphery structure. Our work sheds light on the formation of complex network phenomena.

Information brokers control information flow and hold dominating positions in a social network. We study how a team of individuals with heterogeneous influencing power may gain such advantageous position through establishing new links. In particular, a collaborative brokerage problem aims to find the smallest set of nodes for a team of individuals with different influencing power to cover the entire network. We phrase this problem as an extension to the classical graph domination problem and thus this problem is NP-hard. We show that a polynomial-time solution exists for directed trees. We then develop efficient algorithms over arbitrary directed networks. To evaluate the algorithms, we run experiments over networks generated using well-known random graph models and real-world datasets. Experimental results show that our algorithms produce relatively good solutions with faster speed.

By persistently gathering information over social networks, a person can extract detailed accounts of the lives of others and monitor their daily routines. Such surveillance behaviors have posed serious privacy concerns. This paper addresses the question, "who is surveilling you through social networking?". Viewing a network as interconnected agents who interact through posting and retrieving information, we provide a measure to quantify the level of attention a person pays towards another. This measure allows us to capture online interpersonal surveillance.

Network integration refers to a process of building links between two networks so that they dissolve into a single unified network. Togetherness measures the proximity of these two networks as they integrate; this notion is fundamental to social networks as it is relevant to important concepts such as trust, coherence and solidarity. In this paper, we study the algorithmic nature of network integration and formally introduce three notions of togetherness. We analyze the corresponding computational problems of network integration: Given two networks and a desired level of togetherness, build links between members of these networks so that the overall network meets the togetherness criterion. We analyze optimal solutions to this problem, describe several heuristics and compare their performance through experimental analysis.

An organisational structure consists of a network where employees are connected by working and social ties. Analysing this network, one can discover valuable insights into information flow within the organisation. Moreover, properly defined centrality measures reveal the distribution of power and, therefore, important individuals in the network. We develop this idea and propose a model that is consistent with management theory, and that captures main traits of large corporations. The carcass of the model is an organisational hierarchy. We extend it by allowing additional types of connections such as collaboration, consultation, and friendship. Having both reporting and non-reporting interpersonal ties, our model supports a multilevel approach to social networks. We then formally define power and stability in organisations. These notions enable us to analyse a range of organisational phenomena such as limited hierarchy height, restructuring through flattening, and impact of non-reporting ties. We support our framework with examples and case studies.