Multimodal graphs, where nodes contain heterogeneous features such as images and text, are increasingly common in real-world applications. Effectively learning on such graphs requires both adaptive intra-modal message passing and efficient inter-modal aggregation. However, most existing approaches to multimodal graph learning are typically extended from conventional graph neural networks and rely on static structures or dense attention, which limit flexibility and expressive node embedding learning. In this paper, we propose a novel multimodal graph representation learning framework with Dynamic information Pathways (DiP). By introducing modality-specific pseudo nodes, DiP enables dynamic message routing within each modality via proximity-guided pseudo-node interactions and captures inter-modality dependence through efficient information pathways in a shared state space. This design achieves adaptive, expressive, and sparse message propagation across modalities with linear complexity. We conduct the link prediction and node classification tasks to evaluate performance and carry out full experimental analyses. Extensive experiments across multiple benchmarks demonstrate that DiP consistently outperforms baselines.

Multivariate motif discovery aims to identify frequently occurring subsequences within multi-dimensional time series, which is a critical machine learning task with wide applications. However, previous motif discovery algorithms often miss complex multivariate motifs and struggle with high computational costs as data scale and dimensionality grow. We propose a novel learnable multivariate matrix profile method (L-MAP) that captures inter-dimensional dependencies for comprehensive analysis of multivariate time series. The time series is partitioned into subsequences using the Fourier transform in the frequency domain, with locality-sensitive hashing (LSH) assigning them to buckets based on distinct patterns. Each subsequence is modeled as a graph for multivariate fusion, where triplet learning is used to capture cross-dimensional relationships and form graph embeddings. Unlike prior methods relying on Euclidean distance modeling, our graph-based approach computes all-pairs similarity in a latent space, which constructs the multivariate matrix profile from distributions formed by embedding clusters. Extensive experiments on multivariate datasets from diverse domains demonstrate that L-MAP outperforms state-of-the-art methods in motif discovery, offering superior quality, diversity, and scalability efficiency.

Graph Neural Networks (GNNs) have shown remarkable effectiveness across various applications, but their computational complexity poses significant scalability challenges. To this end, GNN-to-MLP Knowledge Distillation (KD) methods transfer relational inductive biases from GNNs to MLPs, equipping MLPs with graph-aware capabilities that rival or even surpass those of their teacher GNNs. However, a theoretical foundation for understanding GNN-to-MLP KD is still missing. In this paper, we provide a theoretical analysis of how knowledge distillation unlocks the potential of MLPs for graph tasks from the perspective of training dynamics. We demonstrate that label alignment in KD fundamentally reshapes the Neural Tangent Kernel (NTK) matrix of student MLPs, enabling them to learn the teacher model’s implicit graph bias. We further investigate finer-grained distillation paradigms and reveal that conventional layer-wise output alignment fails to effectively align the deep-layer graph propagation outcomes. To address this, we propose Dual-Stream Aligned MLP (DA-MLP), which incorporates complementary graph filters in a dual-stream architecture. This approach simultaneously enhances feature space dimensionality for improved representation alignment and preserves graph signals across different frequency bands. Comprehensive experiments on seven benchmark datasets validate that DA-MLP can be seamlessly integrated into existing knowledge distillation frameworks for performance enhancements in both transductive and inductive settings.

The rapid growth of web content has spurred the widespread adoption of on-device AI assistants powered by large language models (LLMs). However, deploying and personalizing these assistants in real-world environments remains challenging due to limited annotation budgets and scarce on-device fine-tuning resources. Existing edge–cloud collaboration frameworks typically rely on costly cloud-based supervision or perform full-layer finetuning, leading to inefficiencies in both computation and adaptation. To address these limitations, we propose EcoTune, a budget-constrained framework for efficient edge–cloud collaborative adaptation. EcoTune jointly optimizes representative data selection for cloud annotation and selective on-device model adaptation within a unified closed-loop process. Specifically, it employs a multi-armed bandit–based strategy to identify highvalue user interactions for cloud supervision and a layer importance–driven adaptation mechanism to update only critical components of the small language model (SLM). This coordinated optimization enables dynamic, resource-efficient personalization under stringent annotation and tuning budgets. Experiments on real-world testbeds demonstrate that EcoTune achieves up to 20%-60% reduction in annotation costs and significantly lowers fine-tuning memory consumption compared to state-of-the-art baselines, providing a practical and scalable solution for personalized on-device LLMs.

Graph Neural Networks (GNNs) have proven effective and typically benefit from pre-training on accessible graphs to enhance performance on tasks with limited labeled data. However, existing GNNs are constrained by the ``one-domain-one-model'' limitation, which restricts their effectiveness across diverse graph domains. In this paper, we tackle this problem by developing a method called Multi-Domain Pre-training for a Unified GNN Model (MDP-GNN). This method is based on the philosophical notion that everything is interconnected, suggesting that a latent meta-domain exists to encompass the diverse graph domains and their interconnections. MDP-GNN seeks to identify and utilize this meta-domain to train a unified GNN model through three core strategies. Firstly, it integrates node feature semantics from different domains to create unified representations. Secondly, it employs a bi-level learning strategy to build a domain-synthesized network that identifies latent connections to facilitate cross-domain knowledge transfer. Thirdly, it uses Wasserstein distance to map diverse domains into the common meta-domain for graph distribution alignment. We validate the effectiveness of MDP-GNN through theoretical analysis and extensive experiments on four real-world graph datasets, showing its superiority in enhancing GNN performance across diverse domains.

Graph Neural Networks (GNNs) have demonstrated remarkable effectiveness across various tasks but are often hindered by their high computational overhead. GNN-to-MLP distillation provides a promising remedy by transferring knowledge from complex GNNs to lightweight MLPs. However, existing methods largely overlook the differences in aggregation mechanisms and heterogeneous architectures. Simplifying such intricate information into MLP potentially causes information loss or distortion, ultimately resulting in suboptimal performance. This paper proposes an aggregation mechanism enhanced GNN distillation framework (AMEND). AMEND introduces multi-scope aggregation context preservation to replicate the teacher's broad aggregation scopes and an aggregation-enhanced centered kernel alignment method to match the teacher's aggregation patterns. To ensure efficient and robust knowledge transfer, we integrate a manifold mixup strategy, enabling the student to capture the teacher's insights into mixed data distributions. Experimental results on 8 standard and 4 large-scale datasets demonstrate that AMEND consistently outperforms state-of-the-art distillation methods.

Probabilistic time series forecasting has attracted an increasing attention in machine learning community for its potential applications in the fields of renewable energy, traffic management, healthcare, etc. Previous research mainly focused on extracting long-range dependencies for point-wise prediction, which fail to capture complex temporal patterns and statistical characteristics for probabilistic analysis. In this paper, we propose a novel pattern-mixture decomposition method that decomposes long-term series into quantile drift, divergence patterns, and Gaussian mixture components, which can effectively capture the intricate temporal patterns and stochastic characteristics in time series. Based on pattern-mixture decomposition, we propose a novel Transformer-based model called QuantileFormer for probabilistic time series forecasting. It takes the the comprehensive drift-divergence mixture patterns as features, and designs a variational inference based fusion Transformer architecture to generate quantile prediction results. Extensive experiments show that the proposed method consistently boosts the baseline methods by a large margin and achieves state-of-the-art performance on six real-world benchmarks.

Graph Neural Networks (GNNs) have emerged as a powerful tool for modeling graph-structured data, exhibiting remarkable potential in applications such as social networks, recommendation systems, and molecular structures. However, the conventional GNNs perform node-level feature aggregation from neighbors without considering graph-label information, which leads to the misaligned embedding problem that may cause a detrimental effect on graph-level tasks such as graph classification. In this paper, we propose a novel label-attentive distillation method called LAD-GNN for graph representation learning to solve this problem. It alternatively trains a teacher model and a student GNN with a distillation-based approach. In the teacher model, a label-attentive encoder is proposed to encode the label information fusing with the node features to generate ideal embedding. In the student model, the ideal embedding is used as intermediate supervision to urge the student GNN to learn class-friendly node embedding to facilitate graph-level tasks. Generally, LAD-GNN is an enhanced GNN training approach that can be incorporated with arbitrary GNN backbone to improve performance without significant increase of computational cost. Extensive experiments with 7 GNN backbones based on 10 benchmark datasets show that LAD-GNN improves the SOTA GNNs in graph classification accuracy. The source codes of LAD-GNN are publicly available on https://github.com/XiaobinHong/LAD-GNN.

Graph Neural Networks (GNNs) have proven effective in various scenarios. A key strategy involves pre-training existing graphs to extract knowledge that can be transferred to improve performance on downstream tasks, reducing the need for extensive labeled data. However, previous works commonly assumed that pre-training and fine-tuning occur in the same or closely related domains. A limitation is that for each individual graph without accessible pre-training data, a GNN must be trained from scratch, imposing high training overhead and hindering the ability of generalization. In this paper, we address the GNN multi-domain pre-training problem, which intends to pre-train a transferable GNN model from heterogeneous multi-source graph domains and then apply it in an unseen one with minor fine-tuning costs. To this end, we propose a scaLA ble Multi-source Pre-training (LAMP) method. For pre-training, LAMP presents a graph dual-distillation approach to distill massive knowledge from various graph domains to form synthetic homogeneous graphs. Simultaneously, high-level meta-knowledge from the synthetic graphs is extracted to train the GNN model, whose capability can be adjusted according to target graph contexts through a co-training modulation architecture. For fine-tuning, LAMP respectively aligns the target graph distribution, graph context, and graph task with the pretext so that the downstream task in the unseen domain can be reshaped to leverage the transferable knowledge efficiently. Extensive experiments on four different graph domain datasets show the superiority of LAMP.

Graph meta learning aims to learn historical knowledge from training graph neural networks (GNNs) models and adapt it to downstream learning tasks in a target graph, which has drawn increasing attention due to its ability of knowledge transfer and fast adaptation. While existing graph meta learning approaches assume the learning tasks are from the same graph domain but lack the solution for multi-domain adaptation. In this paper, we address the multi-domain generalized graph meta learning problem, which is challenging due to non-Euclidean data, inequivalent feature spaces, and heterogeneous distributions. To this end, we propose a novel solution called MD-Gram for multi-domain graph generalization. It introduces an empirical graph generalization method that uses empirical vectors to form a unified expression of non-Euclidean graph data. Then it proposes a multi-domain graphs transformation approach to transform the learning tasks from multiple source-domain graphs with inequivalent feature spaces into a common domain, where graph meta learning is conducted to learn generalized knowledge. It further adopts a domain-specific GNN enhancement method to learn a customized GNN model to achieve fast adaptation in the unseen target domain. Extensive experiments based on four real-world graph domain datasets show that the proposed method significantly outperforms the state-of-the-art in multi-domain graph meta learning tasks.

Influence maximization is the problem of finding a set of seed nodes in the network that maximizes the influence spread, which has become an important topic in social network analysis. Conventional influence maximization algorithms cause “unfair" influence spread among different groups in the population, which could lead to severe bias in public opinion dissemination and viral marketing. To address this issue, we formulate the fair influence maximization problem concerning the trade-off between influence maximization and group fairness. For the purpose of solving the fair influence maximization problem in large-scale social networks efficiently, we propose a novel attribute-based reverse influence sampling (ABRIS) framework. This framework intends to estimate influence in specific groups with guarantee through an attribute-based hypergraph so that we can select seed nodes strategically. Therefore, under the ABRIS framework, we design two different node selection algorithms, ABRIS-G and ABRIS-T. ABRIS-G selects nodes in a greedy scheduling way. ABRIS-T adopts a two-phase node selection method. These algorithms run efficiently and achieve a good trade-off between influence maximization and group fairness. Extensive experiments on six real-world social networks show that our algorithms significantly outperform the state-of-the-art approaches. This article appears in the AI & Society track.

Graph Convolutional Networks (GCNs) are popular for learning representation of graph data and have a wide range of applications in social networks, recommendation systems, etc. However, training GCN models for large networks is resource intensive and time consuming, which hinders them from real deployment. The existing GCN training methods intended to optimize the sampling of mini-batches for stochastic gradient descent to accelerate training process, which did not reduce the problem size and had limited reduction in computation complexity. In this paper, we argue that a GCN can be trained with a sampled subgraph to produce approximate node representations, which inspires us a novel perspective to accelerate GCN training via network sampling. To this end, we propose a label-centric cumulative sampling (LCS) framework for training GCNs for large graphs. The proposed method constructs a subgraph cumulatively based on probabilistic sampling, and trains the GCN model iteratively to generate approximate node representations. The optimality of LCS is theoretically guaranteed to minimize the bias during node aggregation procedure in GCN training. Extensive experiments based on four real-world network datasets show that the LCS framework accelerates the training for the state-of-the-art GCN models up to 17x without causing noteworthy model accuracy drop.

Katz centrality is a fundamental concept to measure the influence of a vertex in a social network. However, existing approaches to calculating Katz centrality in a large-scale network are unpractical and computationally expensive. In this article, we propose a novel method to estimate Katz centrality based on graph sampling techniques, which object to achieve comparable estimation accuracy of the state-of-the-arts with much lower computational complexity. Specifically, we develop a Horvitz–Thompson estimate for Katz centrality by using a multi-round sampling approach and deriving an unbiased mean value estimator. We further propose SAKE , a S ampling-based A lgorithm for fast K atz centrality E stimation. We prove that the estimator calculated by SAKE is probabilistically guaranteed to be within an additive error from the exact value. Extensive evaluation experiments based on four real-world networks show that the proposed algorithm can estimate Katz centralities for partial vertices with low sampling rate, low computation time, and it works well in identifying high influence vertices in social networks.

Large private and government networks are often subjected to attacks like data extrusion and service disruption. Existing anomaly detection systems use offline supervised learning and employ experts for labeling. Hence they cannot detect anomalies in real-time. Even though unsupervised algorithms are increasingly used nowadays, they cannot readily adapt to newer threats. Moreover, many such systems also suffer from high cost of storage and require extensive computational resources. In this paper, we propose ADA: Adaptive Deep Log Anomaly Detector, an unsupervised online deep neural network framework that leverages LSTM networks and regularly adapts to newer log patterns to ensure accurate anomaly detection. In ADA, an adaptive model selection strategy is designed to choose pareto-optimal configurations and thereby utilize resources efficiently. Further, a dynamic threshold algorithm is proposed to dictate the optimal threshold based on recently detected events to improve the detection accuracy. We also use the predictions to guide storage of abnormal data and effectively reduce the overall storage cost. We compare ADA with state-of-the-art approaches through leveraging the Los Alamos National Laboratory cyber security dataset and show that ADA accurately detects anomalies with high F1-score ~95% and it is 97 times faster than existing approaches and incurs very low storage cost.

Assessing individual's personality traits has important implications in psychology, sociology, and economics. Conventional personality measurement methods were questionnaire-based, which are time-consuming and manpower-expensive. With the pervasive deployment of mobile communication applications, smartphone usage data was found to relate to people's social behavioral and psychological aspects. In this paper, we propose a deep learning approach to infer people's Big Five personality traits based on smartphone data. Specifically, we collect smartphone usage snapshots with an Android App, and extract features from the collected data. We propose a multi-view multi-task learning approach with a deep neural network model to fuse the extracted features and learn the Big Five personality traits jointly. Extensive experiments based on the real-world smartphone data collected from university volunteers show that the proposed approach significantly outperforms the state-of-the-art algorithms in personality prediction.

Influence maximization in social networks is the problem of finding a set of seed nodes in the network that maximizes the spread of influence under certain information prorogation model, which has become an important topic in social network analysis. In this paper, we show that conventional influence maximization algorithms cause uneven spread of influence among different attribute groups in social networks, which could lead to severer bias in public opinion dissemination and viral marketing. We formulate the balanced influence maximization problem to address the trade-off between influence maximization and attribute balance, and propose a sampling based solution to solve the problem efficiently. To avoid full network exploration, we first propose an attribute-based (AB) sampling method to sample attributed social networks with respect to preserving network structural properties and attribute proportion among user groups. Then we propose an attributed-based reverse influence sampling (AB-RIS) algorithm to select seed nodes from the sampled graph. The proposed AB-RIS algorithm runs efficiently with guaranteed accuracy, and achieves the trade-off between influence maximization and attribute balance. Extensive experiments based on four real-world social network datasets show that AB-RIS significantly outperforms the state-of-the-art approaches in balanced influence maximization.