arXiv subjects

Rong-Hua Li

Publications and source records attributed to Rong-Hua Li.

At least 73 records · Page 4Linked to original sources

arXiv2025

Knowledge-Driven Federated Graph Learning on Model Heterogeneity

Federated graph learning (FGL) has emerged as a promising paradigm for collaborative graph representation learning, enabling multiple parties to jointly train models while preserving data privacy. However, most existing approaches assume homogeneous client models and largely overlook the challenge of model-centric heterogeneous FGL (MHtFGL), which frequently arises in practice when organizations employ graph neural networks (GNNs) of different scales and architectures.Such architectural diversity not only undermines smooth server-side aggregation, which presupposes a unified representation space shared across clients' updates, but also further complicates the transfer and integration of structural knowledge across clients. To address this issue, we propose the Federated Graph Knowledge Collaboration (FedGKC) framework. FedGKC introduces a lightweight Copilot Model on each client to facilitate knowledge exchange while local architectures are heterogeneous across clients, and employs two complementary mechanisms: Client-side Self-Mutual Knowledge Distillation, which transfers effective knowledge between local and copilot models through bidirectional distillation with multi-view perturbation; and Server-side Knowledge-Aware Model Aggregation, which dynamically assigns aggregation weights based on knowledge provided by clients. Extensive experiments on eight benchmark datasets demonstrate that FedGKC achieves an average accuracy gain of 3.88% over baselines in MHtFGL scenarios, while maintaining excellent performance in homogeneous settings.

cs.LG↗

arXiv2025

A Computationally Efficient Framework for Overlapping Community Detection in Large Bipartite Graphs

Community detection, which uncovers closely connected vertex groups in networks, is vital for applications in social networks, recommendation systems, and beyond. Real-world networks often have bipartite structures (vertices in two disjoint sets with inter-set connections), creating unique challenges on specialized community detection methods. Biclique percolation community (BCPC) is widely used to detect cohesive structures in bipartite graphs. A biclique is a complete bipartite subgraph, and a BCPC forms when maximal bicliques connect via adjacency (sharing an (alpha, beta)-biclique). Yet, existing methods for BCPC detection suffer from high time complexity due to the potentially massive maximal biclique adjacency graph (MBAG). To tackle this, we propose a novel partial-BCPC based solution, whose key idea is to use partial-BCPC to reduce the size of the MBAG. A partial-BCPC is a subset of BCPC. Maximal bicliques belonging to the same partial-BCPC must also belong to the same BCPC. Therefore, these maximal bicliques can be grouped as a single vertex in the MBAG, significantly reducing the size of the MBAG. Furthermore, we move beyond the limitations of MBAG and propose a novel BCPC detection approach based on (alpha, beta)-biclique enumeration. This approach detects BCPC by enumerating all (alpha, beta)-bicliques and connecting maximal bicliques sharing the same (alpha, beta)-biclique, which is the condition for maximal bicliques to be adjacent. It also leverages partial-BCPC to significantly prune the enumeration space of (alpha, beta)-biclique. Experiments show that our methods outperform existing methods by nearly three orders of magnitude.

cs.SI↗

arXiv2025

Scalable Similarity Search over Large Attributed Bipartite Graphs

Bipartite graphs are widely used to model relationships between entities of different types, where nodes are divided into two disjoint sets. Similarity search, a fundamental operation that retrieves nodes similar to a given query node, plays a crucial role in various real-world applications, including machine learning and graph clustering. However, existing state-of-the-art methods often struggle to accurately capture the unique structural properties of bipartite graphs or fail to incorporate the informative node attributes, leading to suboptimal performance. Besides, their high computational complexity limits scalability, making them impractical for large graphs with millions of nodes and tens of thousands of attributes. To overcome these challenges, we first introduce Attribute-augmented Hidden Personalized PageRank (AHPP), a novel random walk model designed to blend seamlessly both the higher-order bipartite structure proximity and attribute similarity. We then formulate the similarity search over attributed bipartite graphs as an approximate AHPP problem and propose two efficient push-style local algorithms with provable approximation guarantees. Finally, extensive experiments on real-world and synthetic datasets validate the effectiveness of AHPP and the efficiency of our proposed algorithms when compared with fifteen competitors.

cs.DS↗

arXiv2025

BD-Index: Scalable Biharmonic Distance Queries on Large Graphs via Divide-and-Conquer Indexing

Biharmonic distance (\bd) is a powerful graph distance metric with many applications, including identifying critical links in road networks and mitigating over-squashing problem in \gnn. However, computing \bd\ is extremely difficult, especially on large graphs. In this paper, we focus on the problem of \emph{single-pair} \bd\ query. Existing methods mainly rely on random walk-based approaches, which work well on some graphs but become inefficient when the random walk cannot mix rapidly.To overcome this issue, we first show that the biharmonic distance between two nodes $s,t$, denoted by $b(s,t)$, can be interpreted as the distance between two random walk distributions starting from $s$ and $t$. To estimate these distributions, the required random walk length is large when the underlying graph can be easily cut into smaller pieces. Inspired by this observation, we present novel formulas of \bd to represent $b(s,t)$ by independent random walks within two node sets $\mathcal{V}_s$, $\mathcal{V}_t$ separated by a small \emph{cut set} $\mathcal{V}_{cut}$, where $\mathcal{V}_s\cup\mathcal{V}_t\cup\mathcal{V}_{cut}=\mathcal{V}$ is the set of graph nodes. Building upon this idea, we propose \bindex, a novel index structure which follows a divide-and-conquer strategy. The graph is first cut into pieces so that each part can be processed easily. Then, all the required random walk probabilities can be deterministically computed in a bottom-top manner. When a query comes, only a small part of the index needs to be accessed. We prove that \bindex\ requires $O(n\cdot h)$ space, can be built in $O(n\cdot h\cdot (h+d_{max}))$ time, and answers each query in $O(n\cdot h)$ time, where $h$ is the height of a hierarchy partition tree and $d_{max}$ is the maximum degree, which are both usually much smaller than $n$.

cs.DS↗

arXiv2025

Scalable and Provable Kemeny Constant Computation on Static and Dynamic Graphs: A 2-Forest Sampling Approach

Kemeny constant, defined as the expected hitting time of random walks from a source node to a randomly chosen target node, is a fundamental metric in graph data management with many real-world applications. However, computing it exactly on large graphs is highly challenging, as it requires inverting large graph matrices. Existing solutions mainly rely on approximate random-walk-based methods, which still need large sample sizes and lack strong theoretical guarantees. In this paper, we propose a new approach for approximating the Kemeny constant via 2-forest sampling. We first derive an unbiased estimator expressed through spanning trees by introducing a path mapping technique that establishes a direct correspondence between spanning trees and certain classes of 2-forests. Compared to random walk-based estimators, 2-forest-based estimators yield leads to a better theoretical bound. We further design efficient algorithms to sample and traverse spanning trees, leveraging data structures such as the Binary Indexed Tree (BIT) for optimization. Our theoretical analysis shows that the Kemeny constant can be approximated with relative error $ε$ in $O\left(\frac{Δ^2\bar{d}^2}{ε^2}(τ+ n\min(\log n, Δ))\right)$ time, where $τ$ is the tree-sampling time, $\bar{d}$ is the average degree, and $Δ$ is the graph diameter. This complexity is near-linear in practice. Moreover, existing methods largely target static graphs and lack efficient mechanisms for dynamic updates. To address this, we propose two sample maintenance strategies that partially update samples while preserving accuracy on dynamic graphs. Extensive experiments on 10 large real-world datasets demonstrate that our method consistently outperforms state-of-the-art approaches in both efficiency and accuracy on static and dynamic graphs.

cs.DS↗

arXiv2025

NCSAC: Effective Neural Community Search via Attribute-augmented Conductance

Identifying locally dense communities closely connected to the user-initiated query node is crucial for a wide range of applications. Existing approaches either solely depend on rule-based constraints or exclusively utilize deep learning technologies to identify target communities. Therefore, an important question is proposed: can deep learning be integrated with rule-based constraints to elevate the quality of community search? In this paper, we affirmatively address this question by introducing a novel approach called Neural Community Search via Attribute-augmented Conductance, abbreviated as NCSAC. Specifically, NCSAC first proposes a novel concept of attribute-augmented conductance, which harmoniously blends the (internal and external) structural proximity and the attribute similarity. Then, NCSAC extracts a coarse candidate community of satisfactory quality using the proposed attribute-augmented conductance. Subsequently, NCSAC frames the community search as a graph optimization task, refining the candidate community through sophisticated reinforcement learning techniques, thereby producing high-quality results. Extensive experiments on six real-world graphs and ten competitors demonstrate the superiority of our solutions in terms of accuracy, efficiency, and scalability. Notably, the proposed solution outperforms state-of-the-art methods, achieving an impressive F1-score improvement ranging from 5.3\% to 42.4\%. For reproducibility purposes, the source code is available at https://github.com/longlonglin/ncsac.

cs.SI↗

arXiv2025

Unveiling the Vulnerability of Graph-LLMs: An Interpretable Multi-Dimensional Adversarial Attack on TAGs

Graph Neural Networks (GNNs) have become a pivotal framework for modeling graph-structured data, enabling a wide range of applications from social network analysis to molecular chemistry. By integrating large language models (LLMs), text-attributed graphs (TAGs) enhance node representations with rich textual semantics, significantly boosting the expressive power of graph-based learning. However, this sophisticated synergy introduces critical vulnerabilities, as Graph-LLMs are susceptible to adversarial attacks on both their structural topology and textual attributes. Although specialized attack methods have been designed for each of these aspects, no work has yet unified them into a comprehensive approach. In this work, we propose the Interpretable Multi-Dimensional Graph Attack (IMDGA), a novel human-centric adversarial attack framework designed to orchestrate multi-level perturbations across both graph structure and textual features. IMDGA utilizes three tightly integrated modules to craft attacks that balance interpretability and impact, enabling a deeper understanding of Graph-LLM vulnerabilities. Through rigorous theoretical analysis and comprehensive empirical evaluations on diverse datasets and architectures, IMDGA demonstrates superior interpretability, attack effectiveness, stealthiness, and robustness compared to existing methods. By exposing critical weaknesses in TAG representation learning, this work uncovers a previously underexplored semantic dimension of vulnerability in Graph-LLMs, offering valuable insights for improving their resilience. Our code and resources are publicly available at https://anonymous.4open.science/r/IMDGA-7289.

cs.LG↗

arXiv2025

MagicDock: Toward Docking-oriented De Novo Ligand Design via Gradient Inversion

De novo ligand design is a fundamental task that seeks to generate protein or molecule candidates that can effectively dock with protein receptors and achieve strong binding affinity entirely from scratch. It holds paramount significance for a wide spectrum of biomedical applications. However, most existing studies are constrained by the \textbf{Pseudo De Novo}, \textbf{Limited Docking Modeling}, and \textbf{Inflexible Ligand Type}. To address these issues, we propose MagicDock, a forward-looking framework grounded in the progressive pipeline and differentiable surface modeling. (1) We adopt a well-designed gradient inversion framework. To begin with, general docking knowledge of receptors and ligands is incorporated into the backbone model. Subsequently, the docking knowledge is instantiated as reverse gradient flows by binding prediction, which iteratively guide the de novo generation of ligands. (2) We emphasize differentiable surface modeling in the docking process, leveraging learnable 3D point-cloud representations to precisely capture binding details, thereby ensuring that the generated ligands preserve docking validity through direct and interpretable spatial fingerprints. (3) We introduce customized designs for different ligand types and integrate them into a unified gradient inversion framework with flexible triggers, thereby ensuring broad applicability. Moreover, we provide rigorous theoretical guarantees for each component of MagicDock. Extensive experiments across 9 scenarios demonstrate that MagicDock achieves average improvements of 27.1\% and 11.7\% over SOTA baselines specialized for protein or molecule ligand design, respectively.

cs.LG↗

arXiv2025

FedBook: A Unified Federated Graph Foundation Codebook with Intra-domain and Inter-domain Knowledge Modeling

Foundation models have shown remarkable cross-domain generalization in language and vision, inspiring the development of graph foundation models (GFMs). However, existing GFMs typically assume centralized access to multi-domain graphs, which is often infeasible due to privacy and institutional constraints. Federated Graph Foundation Models (FedGFMs) address this limitation, but their effectiveness fundamentally hinges on constructing a robust global codebook that achieves intra-domain coherence by consolidating mutually reinforcing semantics within each domain, while also maintaining inter-domain diversity by retaining heterogeneous knowledge across domains. To this end, we propose FedBook, a unified federated graph foundation codebook that systematically aggregates clients' local codebooks during server-side federated pre-training. FedBook follows a two-phase process: (1) Intra-domain Collaboration, where low-frequency tokens are refined by referencing more semantically reliable high-frequency tokens across clients to enhance domain-specific coherence; and (2) Inter-domain Integration, where client contributions are weighted by the semantic distinctiveness of their codebooks during the aggregation of the global GFM, thereby preserving cross-domain diversity. Extensive experiments on 8 benchmarks across multiple domains and tasks demonstrate that FedBook consistently outperforms 21 baselines, including isolated supervised learning, FL/FGL, federated adaptations of centralized GFMs, and FedGFM techniques.

cs.LG↗

arXiv2025

DiRW: Path-Aware Digraph Learning for Heterophily

Recently, graph neural network (GNN) has emerged as a powerful representation learning tool for graph-structured data. However, most approaches are tailored for undirected graphs, neglecting the abundant information in the edges of directed graphs (digraphs). In fact, digraphs are widely applied in the real world and confirmed to address heterophily challenges. Despite recent advancements, existing spatial- and spectral-based DiGNNs have limitations due to their complex learning mechanisms and reliance on high-quality topology, resulting in low efficiency and unstable performance. To address these issues, we propose Directed Random Walk (DiRW), a plug-and-play strategy for most spatial-based DiGNNs and also an innovative model which offers a new digraph learning paradigm. Specifically, it utilizes a direction-aware path sampler optimized from the perspectives of walk probability, length, and number in a weight-free manner by considering node profiles and topologies. Building upon this, DiRW incorporates a node-wise learnable path aggregator for generalized node representations. Extensive experiments on 9 datasets demonstrate that DiRW: (1) enhances most spatial-based methods as a plug-and-play strategy; (2) achieves SOTA performance as a new digraph learning paradigm. The source code and data are available at https://github.com/dhsiuu/DiRW.

cs.LG↗

arXiv2025

Two Facets of the Same Optimization Coin: Model Degradation and Representation Collapse in Graph Foundation Models

Inspired by the success of LLMs, GFMs are designed to learn the optimal embedding functions from multi-domain text-attributed graphs for the downstream cross-task generalization capability. Among the diverse architectures, graph VQ-MAE stands out among the increasingly diverse landscape of GFM. This is attributed to its ability to jointly encode topology and textual attributes from multiple domains into discrete embedding spaces with clear semantic boundaries. Despite its potential, domain generalization conflicts cause imperceptible pitfalls. In this paper, we instantiate two of them, and they are just like two sides of the same GFM optimization coin - Side 1 Model Degradation: The encoder and codebook fail to capture the diversity of inputs; Side 2 Representation Collapse: The hidden embedding and codebook vector fail to preserve semantic separability due to constraints from narrow representation subspaces. These two pitfalls (sides) collectively impair the decoder and generate the low-quality reconstructed supervision, causing the GFM optimization dilemma during pre-training (coin). Through empirical investigation, we attribute the above challenges to Information Bottleneck and Regularization Deficit. To address them, we propose MoT - (1) Information Tinker for Two Pitfalls, which utilizes an edge-wise semantic fusion strategy and a mixture-of-codebooks with domain-aware routing to improve information capacity. (2) Regularization Tinker for Optimization Coin, which utilizes two additional regularizations to further improve gradient supervision in our proposed Information Tinker. Notably, as a flexible architecture, MoT adheres to the scaling laws of GFM, offering a controllable model scale. Compared to SOTA baselines, experiments on 22 datasets across 6 domains demonstrate that MoT achieves significant improvements in supervised, few-shot, and zero-shot scenarios.

cs.LG↗

arXiv2025

State Space Models over Directed Graphs

Directed graphs are ubiquitous across numerous domains, where the directionality of edges encodes critical causal dependencies. However, existing GNNs and graph Transformers tailored for directed graphs face two major challenges: (1) effectively capturing long-range causal dependencies derived from directed edges; (2) balancing accuracy and training efficiency when processing large-scale graph datasets. In recent years, state space models (SSMs) have achieved substantial progress in causal sequence tasks, and their variants designed for graphs have demonstrated state-of-the-art accuracy while maintaining high efficiency across various graph learning benchmarks. However, existing graph state space models are exclusively designed for undirected graphs, which limits their performance in directed graph learning. To this end, we propose an innovative approach DirEgo2Token which sequentializes directed graphs via k-hop ego graphs. This marks the first systematic extension of state space models to the field of directed graph learning. Building upon this, we develop DirGraphSSM, a novel directed graph neural network architecture that implements state space models on directed graphs via the message-passing mechanism. Experimental results demonstrate that DirGraphSSM achieves state-of-the-art performance on three representative directed graph learning tasks while attaining competitive performance on two additional tasks with 1.5$\times $ to 2$\times $ training speed improvements compared to existing state-of-the-art models.

cs.LG↗

arXiv2025

Efficient Exact Resistance Distance Computation on Small-Treewidth Graphs: a Labelling Approach

Resistance distance computation is a fundamental problem in graph analysis, yet existing random walk-based methods are limited to approximate solutions and suffer from poor efficiency on small-treewidth graphs (e.g., road networks). In contrast, shortest-path distance computation achieves remarkable efficiency on such graphs by leveraging cut properties and tree decompositions. Motivated by this disparity, we first analyze the cut property of resistance distance. While a direct generalization proves impractical due to costly matrix operations, we overcome this limitation by integrating tree decompositions, revealing that the resistance distance $r(s,t)$ depends only on labels along the paths from $s$ and $t$ to the root of the decomposition. This insight enables compact labelling structures. Based on this, we propose \treeindex, a novel index method that constructs a resistance distance labelling of size $O(n \cdot h_{\mathcal{G}})$ in $O(n \cdot h_{\mathcal{G}}^2 \cdot d_{\max})$ time, where $h_{\mathcal{G}}$ (tree height) and $d_{\max}$ (maximum degree) behave as small constants in many real-world small-treewidth graphs (e.g., road networks). Our labelling supports exact single-pair queries in $O(h_{\mathcal{G}})$ time and single-source queries in $O(n \cdot h_{\mathcal{G}})$ time. Extensive experiments show that TreeIndex substantially outperforms state-of-the-art approaches. For instance, on the full USA road network, it constructs a $405$ GB labelling in $7$ hours (single-threaded) and answers exact single-pair queries in $10^{-3}$ seconds and single-source queries in $190$ seconds--the first exact method scalable to such large graphs.

cs.DB↗

arXiv2025

Optimal $(α,β)$-Dense Subgraph Search in Bipartite Graphs

Dense subgraph search in bipartite graphs is a fundamental problem in graph analysis, with wide-ranging applications in fraud detection, recommendation systems, and social network analysis. The recently proposed $(α, β)$-dense subgraph model has demonstrated superior capability in capturing the intrinsic density structure of bipartite graphs compared to existing alternatives. However, despite its modeling advantages, the $(α, β)$-dense subgraph model lacks efficient support for query processing and dynamic updates, limiting its practical utility in large-scale applications. To address these limitations, we propose BD-Index, a novel index that answers $(α, β)$-dense subgraph queries in optimal time while using only linear space $O(|E|)$, making it well-suited for real-world applications requiring both fast query processing and low memory consumption. We further develop two complementary maintenance strategies for dynamic bipartite graphs to support efficient updates to the BD-Index. The space-efficient strategy updates the index in time complexity of $O(p \cdot |E|^{1.5})$ per edge insertion or deletion, while maintaining a low space cost of $O(|E|)$ (the same as the index itself), where $p$ is typically a small constant in real-world graphs. In contrast, the time-efficient strategy significantly reduces the update time to $O(p \cdot |E|)$ per edge update by maintaining auxiliary orientation structures, at the cost of increased memory usage up to $O(p \cdot |E|)$. These two strategies provide flexible trade-offs between maintenance efficiency and memory usage, enabling BD-Index to adapt to diverse application requirements. Extensive experiments on 10 large-scale real-world datasets demonstrate high efficiency and scalability of our proposed solutions.

cs.DB↗

arXiv2025

Rethinking Client-oriented Federated Graph Learning

As a new distributed graph learning paradigm, Federated Graph Learning (FGL) facilitates collaborative model training across local systems while preserving data privacy. We review existing FGL approaches and categorize their optimization mechanisms into: (1) Server-Client (S-C), where clients upload local model parameters for server-side aggregation and global updates; (2) Client-Client (C-C), which allows direct exchange of information between clients and customizing their local training process. We reveal that C-C shows superior potential due to its refined communication structure. However, existing C-C methods broadcast redundant node representations, incurring high communication costs and privacy risks at the node level. To this end, we propose FedC4, which combines graph Condensation with C-C Collaboration optimization. Specifically, FedC4 employs graph condensation technique to refine the knowledge of each client's graph into a few synthetic embeddings instead of transmitting node-level knowledge. Moreover, FedC4 introduces three novel modules that allow the source client to send distinct node representations tailored to the target client's graph properties. Experiments on eight public real-world datasets show that FedC4 outperforms state-of-the-art baselines in both task performance and communication cost. Our code is now available on https://github.com/Ereshkigal1/FedC4.

cs.LG↗

arXiv2025

Federated Graph Unlearning

The demand for data privacy has led to the development of frameworks like Federated Graph Learning (FGL), which facilitate decentralized model training. However, a significant operational challenge in such systems is adhering to the right to be forgotten. This principle necessitates robust mechanisms for two distinct types of data removal: the selective erasure of specific entities and their associated knowledge from local subgraphs and the wholesale removal of a user's entire dataset and influence. Existing methods often struggle to fully address both unlearning requirements, frequently resulting in incomplete data removal or the persistence of residual knowledge within the system. This work introduces a unified framework, conceived to provide a comprehensive solution to these challenges. The proposed framework employs a bifurcated strategy tailored to the specific unlearning request. For fine-grained Meta Unlearning, it uses prototype gradients to direct the initial local forgetting process, which is then refined by generating adversarial graphs to eliminate any remaining data traces among affected clients. In the case of complete client unlearning, the framework utilizes adversarial graph generation exclusively to purge the departed client's contributions from the remaining network. Extensive experiments on multiple benchmark datasets validate the proposed approach. The framework achieves substantial improvements in model prediction accuracy across both client and meta-unlearning scenarios when compared to existing methods. Furthermore, additional studies confirm its utility as a plug-in module, where it materially enhances the predictive capabilities and unlearning effectiveness of other established methods.

cs.LG↗

arXiv2025

Effective and Efficient Conductance-based Community Search at Billion Scale

Community search is a widely studied semi-supervised graph clustering problem, retrieving a high-quality connected subgraph containing the user-specified query vertex. However, existing methods primarily focus on cohesiveness within the community but ignore the sparsity outside the community, obtaining sub-par results. Inspired by this, we adopt the well-known conductance metric to measure the quality of a community and introduce a novel problem of conductance-based community search (CCS). CCS aims at finding a subgraph with the smallest conductance among all connected subgraphs that contain the query vertex. We prove that the CCS problem is NP-hard. To efficiently query CCS, a four-stage subgraph-conductance-based community search algorithm, SCCS, is proposed. Specifically, we first greatly reduce the entire graph using local sampling techniques. Then, a three-stage local optimization strategy is employed to continuously refine the community quality. Namely, we first utilize a seeding strategy to obtain an initial community to enhance its internal cohesiveness. Then, we iteratively add qualified vertices in the expansion stage to guarantee the internal cohesiveness and external sparsity of the community. Finally, we gradually remove unqualified vertices during the verification stage. Extensive experiments on real-world datasets containing one billion-scale graph and synthetic datasets show the effectiveness, efficiency, and scalability of our solutions.

cs.SI↗

arXiv2025

A Comprehensive Data-centric Overview of Federated Graph Learning

In the era of big data applications, Federated Graph Learning (FGL) has emerged as a prominent solution that reconcile the tradeoff between optimizing the collective intelligence between decentralized datasets holders and preserving sensitive information to maximum. Existing FGL surveys have contributed meaningfully but largely focus on integrating Federated Learning (FL) and Graph Machine Learning (GML), resulting in early stage taxonomies that emphasis on methodology and simulated scenarios. Notably, a data centric perspective, which systematically examines FGL methods through the lens of data properties and usage, remains unadapted to reorganize FGL research, yet it is critical to assess how FGL studies manage to tackle data centric constraints to enhance model performances. This survey propose a two-level data centric taxonomy: Data Characteristics, which categorizes studies based on the structural and distributional properties of datasets used in FGL, and Data Utilization, which analyzes the training procedures and techniques employed to overcome key data centric challenges. Each taxonomy level is defined by three orthogonal criteria, each representing a distinct data centric configuration. Beyond taxonomy, this survey examines FGL integration with Pretrained Large Models, showcases realistic applications, and highlights future direction aligned with emerging trends in GML.

cs.LG↗