Dynamic graph representation learning has become essential for analyzing evolving networks in domains such as social network analysis, recommendation systems, and traffic analysis. However, existing continuous-time methods face three key challenges: (1) some methods depend solely on node-specific memory without effectively incorporating information from neighboring nodes, resulting in embedding staleness; (2) most fail to explicitly capture correlations between node neighborhoods, limiting contextual awareness; and (3) many fail to fully capture the structural dynamics of evolving graphs, especially in absence of rich link attributes. To address these limitations, we introduce TAWRMAC—a novel framework that integrates Temporal Anonymous Walks with Restart, Memory Augmentation, and Neighbor Co-occurrence embedding. TAWRMAC enhances embedding stability through a memory-augmented GNN with fixed-time encoding and improves contextual representation by explicitly capturing neighbor correlations. Additionally, its Temporal Anonymous Walks with Restart mechanism distinguishes between nodes exhibiting repetitive interactions and those forming new connections beyond their immediate neighborhood. This approach captures structural dynamics better and supports strong inductive learning. Extensive experiments on multiple benchmark datasets demonstrate that TAWRMAC consistently outperforms state-of-the-art methods in dynamic link prediction and node classification under both transductive and inductive settings across three different negative sampling strategies. By providing stable, generalizable, and context-aware embeddings, TAWRMAC advances the state of the art in continuous-time dynamic graph learning.
论文检索
输入标题、作者或关键词，从 7,876 篇学术成果中精准定位
Graph-structured data effectively captures complex relationships in diverse domains such as social networks, financial transactions, citation networks, and recommendation systems. Graph Neural Networks (GNNs) excel in learning intricate topological patterns, yielding strong performance on tasks like node classification and link prediction. However, real-world graphs often scale to millions of nodes and billions of directed edges, posing significant computational and storage challenges for GNN training that frequently exceed available hardware limits. Although graph sampling and distillation techniques alleviate these issues by subsampling or creating surrogate graphs, they primarily handle undirected graphs, neglecting directional semantics that are crucial for applications like fraud detection and causal analysis. To address these limitations, we introduce the Directed Graph Distillation (Dir-GD) framework, which combines distributed learning with community detection to divide large directed graphs into independent subgraphs for distributed directed GNN training. This process culminates in parameter aggregation to produce a compact global synthetic graph that preserves essential topology and directionality. Extensive experiments on large-scale datasets, such as the million-node soc-pokec-relationships, demonstrate over 91% accuracy at 0.001 distillation ratios, accompanied by substantial memory and runtime savings. This work pioneers directed graph distillation as a key paradigm for analyzing ultra-large directed graphs, offering a scalable solution that maintains high fidelity in compressed representations.
Graph Foundation Models (GFMs) have emerged as a frontier in graph learning, which are expected to deliver transferable representations across diverse tasks. However, GFMs remain constrained by in-memory bottlenecks: they attempt to encode knowledge into model parameters, which limits semantic capacity, introduces heavy lossy compression with conflicts, and entangles graph representation with the knowledge in ways that hinder efficient adaptation, undermining scalability and interpretability. In this work,we propose RAG-GFM, a Retrieval-Augmented Generation aided Graph Foundation Model that offloads knowledge from parameters and complements parameterized learning. To externalize graph knowledge, we build a dual-modal unified retrieval module, where a semantic store from prefix-structured text and a structural store from centrality-based motif. To preserve heterogeneous information, we design a dual-view alignment objective that contrasts both modalities to capture both content and relational patterns. To enable efficient downstream adaptation, we perform in-context augmentation to enrich supporting instances with retrieved texts and motifs as contextual evidence. Extensive experiments on five benchmark graph datasets demonstrate that RAG-GFM consistently outperforms 13 state-of-the-art baselines in both cross-domain node and graph classification, achieving superior effectiveness and efficiency.
In this paper, we propose Graph Retention Networks (GRNs) as a unified architecture for deep learning on dynamic graphs. The GRN extends the concept of retention into dynamic graph data as graph retention, equipping the model with three key computational paradigms: parallelizable training, low-cost O(1) inference, and long-term chunkwise training. This architecture achieves an optimal balance between efficiency, effectiveness, and scalability. Extensive experiments on benchmark datasets demonstrate its strong performance in both edge-level prediction and node-level classification tasks with significantly reduced training latency, lower GPU memory overhead, and improved inference throughput by up to 86.7x compared to SOTA baselines. The proposed GRN architecture achieves competitive performance across diverse dynamic graph benchmarks, demonstrating its adaptability to a wide range of tasks.
Graph incremental learning aims to sequentially adapt models to evolving graphs while mitigating catastrophic forgetting. This problem becomes particularly challenging due to the simultaneous occurrence of covariate and label distribution shifts, introduced by newly emerging node classes, changes in node feature styles, and additional edges. To address these challenges, we propose DINGLE, a novel framework for both class and domain (class-domain) incremental learning on graphs. DINGLE consists of two key modules: a representation decoupler, which disentangles node representations into domain-invariant semantic factors for classification and domain-specific variation factors, and a teacher-student knowledge distillation module, which facilitates knowledge transfer across tasks while mitigating catastrophic forgetting through memory replay. By leveraging a Representative Node Feature (RNF) bank and an Encoder Parameters (EP) bank, DINGLE ensures effective knowledge retention and adaptation. Extensive experiments on 5 real-world datasets demonstrate that DINGLE outperforms 11 state-of-the-art baselines in class-domain incremental learning, improving classification accuracy while effectively preventing forgetting across tasks.
Automated identification of killer whale call types from continuous acoustic recordings is essential for scalable population monitoring, yet existing general-purpose frameworks such as ANIMAL-SPOT suffer from suboptimal spectrogram resolution and lack strategies tailored to the spectral-temporal characteristics of killer whale vocalizations. We identify two key limitations of the ANIMAL-SPOT framework: (1)~no possibility to choose different architecture of CNN backbone, and (2)~the absence of regularization and class-balancing techniques limits generalization across call types with varying abundance. To address these issues, we propose a framework that combines optimized STFT parameters (FFT size 1024, hop length 172) with label smoothing and targeted oversampling, evaluated across three CNN backbones and five segment lengths. On a dataset of 12 killer whale vocalization classes from Avacha Gulf, Russia, our best configuration (ResNet-18 with 1200\,ms segments) achieves \textbf{97.1\%} segment-level accuracy, compared to \textbf{96.2\%} for the ANIMAL-SPOT baseline --- a relative error reduction of 23.7\%. We further present an interactive demonstration system for uploading recordings and obtaining time-resolved call-type predictions, enabling rapid analysis of passive acoustic monitoring data. Demo video link: https://drive.google.com/file/d/1ITA_52WdnAcyg7zRjIIshutjl6Lp_um1/view?usp=drive_link Presentation slides: https://drive.google.com/file/d/1sd-JH1R5YPa9iRtsbRO-OZxY8-fyglsO/view?usp=drive_link
3D scene generation has rapidly evolved, significantly promoting the innovation of content creation. In this context, interaction techniques serve as a pivotal bridge connecting user intent with the generative models, thereby enabling precise control, real-time feedback and personalized customization of complex 3D scenes. Existing literature reviews predominantly focus on general generative paradigms, or are limited to specific subdomains such as single-object modeling, while often overlooking the systematic classification of interaction mechanisms. To bridge this gap, this work presented a comprehensive survey of interaction techniques in 3D scene generation. We proposed a unified taxonomy that categorized existing methods into three primary paradigms: Interactive Generation, Interactive Editing, and Embodied Interaction. For each category, we analyzed representative methods in terms of controllability, interaction granularity, and physical consistency, and discussed their advantages and limitations. We further summarized commonly used datasets and evaluation protocols for interactive 3D scene generation. Finally, we discussed the future directions toward more physically grounded, multi-modal, and user-centered interactive 3D scene generation systems. A curated list of the related papers mentioned in this work can be found at Awesome-Interactive-Techniques-in-3D-Scene-Generation-Lists.
LLM Ensemble---which involves the comprehensive use of multiple large language models (LLMs), each aimed at handling user queries during downstream inference, to benefit from their individual strengths---has gained substantial attention recently. The widespread availability of LLMs, coupled with their varying strengths and out-of-the-box usability, has profoundly advanced the field of LLM Ensemble. This paper presents the first systematic review of recent developments in LLM Ensemble. First, we introduce our taxonomy of LLM Ensemble and discuss several related research problems. Then, we provide a more in-depth classification of the methods under the broad categories of ``ensemble-before-inference, ensemble-during-inference, ensemble-after-inference'', and review relevant methods. Finally, we introduce related benchmarks and applications, summarize existing studies, and suggest future research directions. GitHub project link is: https://github.com/junchenzhi/Awesome-LLM-Ensemble.
Graph Neural Networks (GNNs) have demonstrated remarkable proficiency in modeling data with graph structures, yet recent research reveals their susceptibility to adversarial attacks. Traditional attack methodologies, which rely on manipulating the original graph or adding links to artificially created nodes, often prove impractical in real-world settings. This paper introduces a novel adversarial scenario involving the injection of an isolated subgraph to deceive both the link recommender and the node classifier within a GNN system. Specifically, the link recommender is mislead to propose links between targeted victim nodes and the subgraph, encouraging users to unintentionally establish connections and that would degrade the node classification accuracy, thereby facilitating a successful attack. To address this, we present the LiSA framework, which employs a dual surrogate model and bi-level optimization to simultaneously meet two adversarial objectives. Extensive experiments on real-world datasets demonstrate the effectiveness of our method.
Deep learning has achieved strong results in modeling sequential data, including event sequences, temporal point processes, and irregular time series. Recently, transformers have largely replaced recurrent networks in these tasks. However, transformers often underperform recurrent networks in classification tasks that aim to predict future targets, such as churn, user reactions, or treatment response. The reason behind this performance gap remains largely underexplored. In this paper, we identify a key limitation of transformers: the lack of a single vector representation that compactly summarizes the evolving state of a sequence. We further show that commonly used contrastive embeddings are poorly suited to capturing the local context needed for accurate forward-looking prediction. To address these challenges, we introduce history tokens, a novel concept that enables the accumulation of historical information during next-token prediction pretraining. Our approach significantly improves transformer-based models, achieving impressive results in finance, e-commerce, and healthcare tasks. The code is publicly available: https://github.com/ivan-chai/pretpp.
Brain connectivity analysis is a fundamental tool for identifying biomarkers and understanding of neurological disorders. Most existing approaches employ graph transformers over undirected functional connectivity networks, which are typically estimated using correlation statistics. Although effective for capturing statistical associations, these models do not represent directed interactions between brain regions that arise from causal relationships. As a result, direction-specific disease mechanisms are not explicitly modeled, and interpretability is often limited. To address this gap, we present BrainCGT, a brain graph transformer designed to model causal connectivity inferred from fMRI time-series data. In this framework, brain networks are modeled as directed graphs with a modular organization, where nodes correspond to individual brain regions and directed edges reflect causal flow of information between them. Direction-aware node representations together with direction-biased attention mechanisms allow the model to capture asymmetric interactions across regions. Experimental results on three large-scale fMRI datasets demonstrate that BrainCGT achieves consistently better performance than existing graph-based methods for neurological disorder classification. In addition, examination of the learned attention structures shows correspondence with established neurobiological pathways, suggesting improved interpretability. These results highlight the importance of incorporating causal directionality into brain graph transformer architectures for robust and interpretable neuroimaging analysis.
Anti-money laundering (AML) systems are important for safe economic trade and for the fight against financial crime. Recently, a number of AML algorithms based on graph neural networks (GNNs) and graph transformers (GTs) have been proposed. Compared to traditional machine learning solutions, these methods have been shown to achieve significantly better detection results. Yet, the state-of-the-art AML algorithms have a key limitation: they fail to jointly address money laundering classification and money laundering sub-network discovery, despite their strong theoretical connection. To bridge this gap, we propose a translation-based AML system (TAML) that is capable of jointly solving both problems within the same latent space. Our extensive experimental evaluation on multiple datasets demonstrates the superiority of TAML over the state-of-the-art in both tasks.
Diabetic retinopathy (DR) and diabetic macular edema (DME) are leading causes of preventable blindness worldwide. Automated screening tools are critical for timely detection at scale, particularly in low-resource settings where access to ophthalmologists is limited. We propose DRDME-Net, a deployment-driven joint learning framework that formulates DR grading as an ordinal regression task and DME detection via a continuous surrogate, rather than conventional classification. This design yields stable risk scores tightly aligned with operational clinical decision-making thresholds. Evaluation on facility and community cohorts demonstrates that DRDME-Net achieves strong performance across severity boundaries. Insights from an initial feasibility pilot further demonstrate its scalability in real-world workflows. These results highlight the potential of DRDME-Net to expand equitable access to timely detection, reduce preventable vision loss, and provide a practical template for integrating AI into population screening initiatives.
Monitoring forest functional diversity is essential to understand ecosystem resilience in the face of rapid environmental change. While existing remote sensing approaches primarily track structural attributes such as canopy density and tree height, functional traits like leaf phenology (evergreen vs. deciduous) and leaf type (broadleaf vs. needleleaf) reveal more direct information about adaptive strategies of tree species. This study presents a scalable machine learning framework for mapping these traits across India at 10 m resolution using Google AlphaEarth Foundations (AEF) embeddings, which capture the complete annual spectral reflectance and radar signatures of the land surface. A key contribution we make is to curate an ML-ready training dataset by combining tree traits information with tree species occurrence data, and to obtain a diverse sample from this data based on spectral time-series to ensure the dataset captures a wide range of phenological dynamics. We then build cross-validation folds to specifically test for spatial generalizability across different eco-regions in India and temporal generalizability across different years, for classifiers learned from the data. Multiple classifiers are evaluated: Random Forest models trained on AEF embedding features achieved the best performance for both classification tasks, outperforming models trained on conventional Sentinel-1 and Sentinel-2 time series while offering seamless deployment in Google Earth Engine. Compared to publicly available land-cover products that encode leaf phenology and leaf type, our model yields significantly higher accuracy while providing outputs at substantially finer spatial resolution. We then observe the outputs of our model over several protected forest areas in India to understand their dynamics over the last 8 years. Our contribution is an analysis-ready open dataset to learn tree traits from remote sensed spectral data, a trained model that is spatially and temporally generalizable, and a demonstration of the insights the model can provide to understand the dynamics of protected forest areas, all of which can be replicated in other areas.
In gene expression analysis, high dimension low sample size data limits the applicability of deep learning, motivating increasing interest in variable-length evolutionary algorithm–based feature selection methods (VLEAs). However, existing VLEAs suffer from unreliable single-metric discrimination under dynamic search-space variation, mismatches between population size and search space dimensionality, and particle performance degradation after search space changes. To this end, a Multiscale-adaptive and Size-adaptive Particle Swarm Optimization (MASA-PSO) is proposed for gene expression analysis. MASA-PSO adopts a multiscale-adaptive weighting framework to explore feature subsets that distinguish between-class sample distributions during search spaces changes, and theoretically proves it enables the collaborative evaluation of multiple metrics. Meanwhile, it proposes an adaptive population division that explicitly models the functional relationship between the population size and the search space to resolve the mismatch. Furthermore, a particle degradation phenomenon impairing the performance of VLEAs is observed and alleviated through a hybrid elite strategy. Experiments on ten gene expression datasets verify that MASA-PSO outperforms state-of-the-art methods in classification accuracy while capturing smaller feature subsets.