Large language models (LLMs) are widely used for question answering (QA) but can generate biased or stereotype-driven answers due to demographic associations learned during pre-training. Existing mitigation strategies often rely on model access or fine-tuning, which limits their applicability to closed-source LLMs. We propose a Causal Front Door Prompting framework (CFDP) that reduces demographic influence by intervening on the chain of thought reasoning, which is treated as an observable mediator. CFDP samples and clusters multiple reasoning traces and estimates answer probabilities through weighted aggregation. Experiments on two widely used bias-sensitive QA benchmarks, BBQ and Stereotype, across major LLMs show that CFDP consistently improves fairness metrics without sacrificing QA accuracy. Ablation and sensitivity analyses confirm the value of each component, indicating that causal intervention on reasoning provides an effective and practical approach for bias mitigation in LLM-based QA.

Model transferability estimation is a task-adaptive pre-trained model selection problem, aiming to determine the optimal model for target dataset from a model hub pre-trained on source dataset without fine-tuning. Although existing model transferability evaluation methods have made some progress, they mainly focus on image or text data in CV and NLP. In contrast, the graph structural data with GNNs models is still underexplored, due to the complexity of the graph structure and the limitations of the generalization ability of GNN models under distribution shift. To fill this blank, we first propose a Graph Neural Network Model Transferability Estimation method via decomposition-augmented discriminant analysis, named GNNMTE, to evaluate the transferability of GNN models on target graph dataset without fine-tuning. It only calculates the GNNMTE score to determine whether it can be effectively transferred to target graph dataset and better select the optimal model for the target graph dataset. Specifically, our proposed \method contains three core components: (1) Dual-block SVD fusion for obtaining the corresponding principal component information; (2) Adaptive weighting by singular value ratio for guiding the extraction of important principal component information on graph data; (3) Graph discriminant analysis for finding the optimal projection direction that separates the classes of graph data. Extensive experimental results on cross-domain graph datasets achieve excellent results, demonstrating powerful superiority.

Unsupervised graph domain adaptation (UGDA) aims to transfer knowledge from a labeled source graph to an unlabeled target graph, addressing the performance degradation caused by distributional shifts in node attributes and graph structures across domains. Despite recent progress, existing UGDA approaches still face two key challenges: (C1) Data-level: Most methods rely on a single source domain, overlooking the complementary knowledge that could be leveraged from multiple sources. (C2) Model-level: Many UGDA models emphasize complex, handcrafted Graph neural network (GNN) architectures, while simpler yet effective designs with propagation (P) & transformation (T) pipeline remain underexplored. To address these challenges, in this paper, we propose a novel approach, which leverages Concise Propagation–Transformation pipeline for multi-source unsupervised Graph Domain Adaptation, dubbed as CPT-GDA, to better capture complementary knowledge from multiple sources in an efficient manner. Specifically, the proposed CPT-GDA adopts a dual-branch GNN architecture with different depths of propagation but the same P-T patterns, which enables the model to efficiently learn node representations to mitigate domain discrepancy. Meanwhile, to facilitate effective knowledge transfer across graphs, we derive three optimization objectives: (1) the classifier loss to learn discriminative representations; (2) the alignment loss weighted by the graph Wasserstein distance to align the structure and feature distribution; and (3) the pseudo-label loss to refine target node representations. Extensive experiments on real-world datasets confirm that the proposed method outperforms recent state-of-the-art baselines, demonstrating its effectiveness.

Recent years have witnessed fast developments of graph neural networks (GNNs) that have benefited myriad graph analytic tasks and applications. Most GNNs rely on the homophily assumption that nodes belonging to the same class are more likely to be connected. However, as a ubiquitous graph property in numerous real-world scenarios, heterophily, i.e., nodes with different labels tend to be linked, significantly limits the performance of tailor-made homophilic GNNs. Hence, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">GNNs for heterophilic graphs</i> are gaining increasing research attention to enhance graph learning with heterophily. In this paper, we provide a comprehensive review of GNNs for heterophilic graphs. Specifically, we propose a systematic taxonomy that governs existing heterophilic GNN models, along with general summaries and detailed analyses. Furthermore, we discuss the relationship between heterophily and various graph research domains, aiming to facilitate the development of more effective GNNs across a spectrum of practical applications and learning tasks in the graph research community. In the end, we point out potential directions to advance and inspire future research and applications on heterophilic graph learning with GNNs.

Graph fraud detection (GFD) has rapidly advanced in protecting online services by identifying malicious fraudsters. Recent supervised GFD research highlights that heterophilic connections between fraudster and user greatly impacts detection performance, where the fraudsters tend to camouflage themselves by building more connections to benign users. Despite their promising performance, their label reliance limits its application in unsupervised scenarios; Additionally, accurately capturing complex and diverse heterophily patterns without labels poses a further challenge. Therefore, we propose a Heterophily-guided Unsupervised Graph fraud dEtection approach (HUGE) for unsupervised GFD, which contains two essential components: a heterophily estimation module and an alignment-based fraud detection module. In the heterophily estimation module, we design a novel unsupervised heterophily metric called HALO, which captures the critical graph properties for GFD, enabling its outstanding ability to estimate heterophily with attributes. In the alignment-based fraud detection module, we develop a joint MLP-GNN architecture with ranking loss and asymmetric alignment loss. The ranking loss aligns the predicted fraud score with the relative order of HALO, providing an extra robustness guarantee by comparing heterophily between non-adjacent nodes. Moreover, the asymmetric alignment loss effectively utilizes structural information to alleviate the feature-smooth effects. Extensive experiments on six datasets demonstrate that HUGE consistently outperforms competitors, showcasing its effectiveness and robustness.

Ocean salinity plays a vital role in circulation, climate, and marine ecosystems, yet its measurement is often sparse, irregular, and noisy, especially in drifter-based datasets. Traditional approaches, such as remote sensing and optimal interpolation, rely on linearity and stationarity, and are limited by cloud cover, sensor drift, and low satellite revisit rates. While machine learning models offer flexibility, they often fail under severe sparsity and lack principled ways to incorporate physical covariates without specialized sensors. In this paper, we introduce the OceAn Salinity Imputation System, a novel diffusion adversarial framework designed to address these challenges by: (1) employing a transformer-based global dependency capturing module to learn long-range spatio-temporal correlations from sparse trajectories; (2) constructing a generative imputation model that conditions on easily observed tidal covariates to progressively refine imputed salinity fields; and (3) using a scheduler diffusion method to enhance the model's robustness. This unified architecture exploits the periodic nature of tidal signals as a proxy for unmeasured physical drivers, without the need for additional equipment. We evaluate OASIS on four benchmark datasets, including one real-world measurement from Fort Pierce Inlet and three simulated Gulf of Mexico trajectories. Results show consistent improvements over both traditional and neural baselines, achieving up to 52.5% reduction in MAE compared to Kriging. We also develop a lightweight, web-based deployment system that enables salinity imputation through interactive and batch interfaces, available at: https://github.com/yfeng77/OASIS.

As privacy protection gains momentum, federated learning has emerged as a cutting-edge approach in medical image analysis. However, the intricacies of medical image segmentation task have led to a dearth of research in this domain, with existing studies falling short in tackling two pivotal challenges: The traditional model with the uniform global model underperforms for certain clients due to the heterogeneity and non-Independent Identically Distributed(non-IID) data across medical institutions. And the communication between the server and clients often incurs significant time costs. This paper introduces a novel Personalized Asynchronous Federated learning for Medical Image Segmentation model, dubbed PAFedMIS, to mitigate the negative impact of the heterogeneous data and fully utilized the waiting time, in medical image segmentation. Comprehensive experiments on ISIC2018 demonstrate the enhanced model accuracy and training efficiency of PAFedMIS.

Dynamic graph neural networks (DGNNs) have emerged as a leading paradigm for learning from dynamic graphs, which are commonly used to model real-world systems and applications. However, due to the evolving nature of dynamic graph data distributions over time, well-trained DGNNs often face significant performance uncertainty when inferring on unseen and unlabeled test graphs in practical deployment. In this case, evaluating the performance of deployed DGNNs at test time is crucial to determine whether a well-trained DGNN is suited for inference on an unseen dynamic test graph. In this work, we introduce a new research problem: DGNN model evaluation, which aims to assess the performance of a specific DGNN model trained on observed dynamic graphs by estimating its performance on unseen dynamic graphs during test time. Specifically, we propose a Dynamic Graph neural network Evaluator, dubbed DYGEvAL, toaddress this new problem. The proposed DyGEvAL involves a two-stage framework: (1) test-time dynamic graph simulation, which captures the training-test distributional differences as supervision signals and trains an evaluator; and (2) DyGEvAL development and training, which accurately estimates the performance of the well-trained DGNN model on the test-time dynamic graphs. Extensive experiments demonstrate that the proposed DyGEvAL serves as an effective evaluator for assessing various DGNN backbones across different dynamic graphs under distribution shifts.

Recent advancements in test-time adaptation (TTA) offer promising solutions for mitigating performance degradation caused by distribution shifts. However, they may fall short in practical deployment of GNNs during test time, due to the significant reliance on impractical retraining or modifications to online GNN models. To address such challenges, in this work, we propose a novel method, i.e., Test-Time Graph REBirth, dubbed TT-GREB, to effectively generalize the well-trained GNN models to the test-time graphs under distribution shifts by directly manipulating the test graph data. Concretely, we develop an overall framework designed by two principles for obtaining newly reborn test graphs, corresponding to two sub-modules: (1) prototype extractor for re-extracting the environment-invariant features of the test-time graph; and (2) environment refiner for re-fining the environment-varying features to explore the potential shifts. Furthermore, we propose a dual test-time graph contrastive learning objective with an effective iterative optimization strategy to obtain optimal prototype components and environmental components of the test graph. Extensive experiments on real-world graphs under diverse test-time distribution shifts verify the effectiveness of our proposed method, showcasing its superior ability to manipulate test-time graphs for better GNN generalization ability.

Federated learning (FL) is a machine learning approach where multiple participants train a model together without sharing their privacy data. The challenge of long-tail data heterogeneity in FL causes imbalanced data distribution among clients and significant disparities in data quantities across different classes. To tackle the long-tail distribution in FL, in this paper, we draw inspiration from the equiangular tight frame to establish a fixed balanced classifier, enhancing the model’s generalization ability for classes with fewer instances. Therefore, feature extractors and a loss aligned with fixed classifiers are designed to address the long-tail distribution in FL. The algorithm also utilizes Sample Standardization and Batch Normalization to standardize the feature space of samples, preventing the impact of the magnitude difference of features across different classes on the prediction probability. In addition, we also propose a logit adjustment loss under a mixed low-temperature setting. Experiments demonstrate that our algorithm outperforms state-of-the-art methods in FL settings with long-tail distribution.

In this work, we address the test-time adaptation challenge in graph neural networks (GNNs), focusing on overcoming the limitations in flexibility and generalization inherent in existing data-centric approaches. To this end, we propose a novel research problem, test-time graph neural dataset search, which seeks to learn a parameterized test-time graph distribution to enhance the inference performance of unseen test graphs on well-trained GNNs. Specifically, we propose a generative Projection based test-time Graph Neural Dataset Search method, named PGNDS, which maps the unseen test graph distribution back to the known training distribution through a generation process guided by well-trained GNNs. The proposed PGNDS framework consists of three key modules: (1) dual conditional diffusion for GNN-guided generative projection through test-back-to-training distribution mapping; (2) dynamic search from the generative sampling space to select the most expressive test graphs; (3) ensemble inference to aggregate information from original and adapted test graphs. Extensive experiments on real-world graphs demonstrate the superior ability of our proposed PGNDS for improved test-time GNN inference.

Distribution shifts in recommender systems between training and testing in user-item interactions lead to inaccurate recommendations. Despite the promising performance of test-time adaptation technology in various domains, it still faces challenges in recommender systems due to the impracticality of fine-tuning models and the infeasibility of obtaining test-time labels. To address these challenges, we first propose a Test-Time Adaptation framework for Graph-based Recommender system, named TTA-GREC, to dynamically adapt user-item graphs at test time in a data-centric way, handling distribution shifts effectively. Specifically, our TTA-GREC targets KG-enhanced GNN-based recommender systems with three core components: (1) Pseudo-label guided UI graph transformation for adaptive improvement; (2) Rationale score guided KG graph revision for semantic enhancement; and (3) Sampling-based self-supervised adaptation for contrastive learning. Experiments demonstrate TTA-GREC's superiority at test time and provide new data-centric insights on test-time adaptation for better recommender system inference.

Privacy and security concerns are becoming increasingly critical for recommender systems, as model extraction attack provides an effective way to probe system robustness by replicating the model’s recommendation logic — potentially exposing sensitive user preferences and proprietary algorithmic knowledge. Despite the promising performance of existing model extraction methods, they still face two key challenges: unrealistic assumptions on the requirement of accessible member or surrogate data and generalization problem where surrogate model architecture constraints lead to overfitting on generated data. To tackle these challenges, in this paper, we first thoroughly analyze how the architecture of surrogate models influences extraction attack performance, highlighting the superior effectiveness of the graph convolution architecture. Based on this, we propose a novel Data-free Black-box Graph convolution-based Recommender Model Extraction method, dubbed DBGRME. Specifically, DBGRME contains: (1) an interaction generator to alleviate the need for member data requirements in a data-free scenario; and (2) a generalization-aware graph convolution-based surrogate model to capture diverse and complex recommender interaction patterns for mitigating the overfitting issue. Experimental results on various datasets and victim models demonstrate the superiority of our attack in data-free scenarios (e.g., surpassing PTQ data-require methods with 17.4% improvement on LightGCN). Code is available: \url{https://github.com/Vencent-Won/DBGRME.git}.

Evaluating the performance of a well-trained GNN model on real-world graphs is a pivotal step for reliable GNN online deployment and serving. Due to a lack of test node labels and unknown potential training-test graph data distribution shifts, conventional model evaluation encounters limitations in calculating performance metrics (e.g., test error) and measuring graph data-level discrepancies, particularly when the training graph used for developing GNNs remains unobserved during test time. In this paper, we study a new research problem, online GNN evaluation, which aims to provide valuable insights into the well-trained GNNs's ability to effectively generalize to real-world unlabeled graphs under the test-time graph distribution shifts. Concretely, we develop an effective learning behavior discrepancy score, dubbed LeBeD, to estimate the test-time generalization errors of well-trained GNN models. Through a novel GNN re-training strategy with a parameter-free optimality criterion, the proposed LeBeD comprehensively integrates learning behavior discrepancies from both node prediction and structure reconstruction perspectives. This enables the effective evaluation of the well-trained GNNs' ability to capture test node semantics and structural representations, making it an expressive metric for estimating the generalization error in online GNN evaluation. Extensive experiments on real-world test graphs under diverse graph distribution shifts could verify the effectiveness of the proposed method, revealing its strong correlation with ground-truth test errors on various well-trained GNN models.

Evaluating the performance of graph neural networks (GNNs) is an essential task for practical GNN model deployment and serving, as deployed GNNs face significant performance uncertainty when inferring on unseen and unlabeled test graphs, due to mismatched training-test graph distributions. In this paper, we study a *new* problem, **GNN model evaluation**, that aims to assess the performance of a specific GNN model trained on labeled and observed graphs, by precisely estimating its performance (e.g., node classification accuracy) on unseen graphs without labels. Concretely, we propose a two-stage GNN model evaluation framework, including (1) DiscGraph set construction and (2) GNNEvaluator training and inference. The DiscGraph set captures wide-range and diverse graph data distribution discrepancies through a discrepancy measurement function, which exploits the GNN outputs of latent node embeddings and node class predictions. Under the effective training supervision from the DiscGraph set, GNNEvaluator learns to precisely estimate node classification accuracy of the to-be-evaluated GNN model and makes an accurate inference for evaluating GNN model performance. Extensive experiments on real-world unseen and unlabeled test graphs demonstrate the effectiveness of our proposed method for GNN model evaluation.

Graph condensation, which reduces the size of a large-scale graph by synthesizing a small-scale condensed graph as its substitution, has immediate benefits for various graph learning tasks. However, existing graph condensation methods rely on the joint optimization of nodes and structures in the condensed graph, and overlook critical issues in effectiveness and generalization ability. In this paper, we advocate a new Structure-Free Graph Condensation paradigm, named SFGC, to distill a large-scale graph into a small-scale graph node set without explicit graph structures, i.e., graph-free data. Our idea is to implicitly encode topology structure information into the node attributes in the synthesized graph-free data, whose topology is reduced to an identity matrix. Specifically, SFGC contains two collaborative components: (1) a training trajectory meta-matching scheme for effectively synthesizing small-scale graph-free data; (2) a graph neural feature score metric for dynamically evaluating the quality of the condensed data. Through training trajectory meta-matching, SFGC aligns the long-term GNN learning behaviors between the large-scale graph and the condensed small-scale graph-free data, ensuring comprehensive and compact transfer of informative knowledge to the graph-free data. Afterward, the underlying condensed graph-free data would be dynamically evaluated with the graph neural feature score, which is a closed-form metric for ensuring the excellent expressiveness of the condensed graph-free data. Extensive experiments verify the superiority of SFGC across different condensation ratios.

Graph neural architecture search (NAS) has gained popularity in automatically designing powerful graph neural networks (GNNs) with relieving human efforts. However, existing graph NAS methods mainly work under the homophily assumption and overlook another important graph property, i.e., heterophily, which exists widely in various real-world applications. To date, automated heterophilic graph learning with NAS is still a research blank to be filled in. Due to the complexity and variety of heterophilic graphs, the critical challenge of heterophilic graph NAS mainly lies in developing the heterophily-specific search space and strategy. Therefore, in this paper, we propose a novel automated graph neural network on heterophilic graphs, namely Auto-HeG, to automatically build heterophilic GNN models with expressive learning abilities. Specifically, Auto-HeG incorporates heterophily into all stages of automatic heterophilic graph learning, including search space design, supernet training, and architecture selection. Through the diverse message-passing scheme with joint micro-level and macro-level designs, we first build a comprehensive heterophilic GNN search space, enabling Auto-HeG to integrate complex and various heterophily of graphs. With a progressive supernet training strategy, we dynamically shrink the initial search space according to layer-wise variation of heterophily, resulting in a compact and efficient supernet. Taking a heterophily-aware distance criterion as the guidance, we conduct heterophilic architecture selection in the leave-one-out pattern, so that specialized and expressive heterophilic GNN architectures can be derived. Extensive experiments illustrate the superiority of Auto-HeG in developing excellent heterophilic GNNs to human-designed models and graph NAS models.

Convolutional neural network (CNN) based image segmentation has been widely used in analyzing medical images and benefited many real-world disease diagnosis applications. However, existing advanced CNN-based medical image segmentation models usually contain numerous parameters that require massive computation and memory, limiting the applicability of these models in the data-constrained or hardware-constrained environments. By leveraging the recently proposed neural architecture search (NAS), this paper presents a novel approach, dubbed Thrifty NAS, to design computation and memory-efficient models for medical image segmentation automatically. The searched models by Thrifty NAS are with much fewer parameters while retaining competitive performance. More specifically, we design a micro level space for cell structure search and a macro level cell path for better network structure modeling. Extensive experimental results in different medical image datasets verify the effectiveness of the proposed method with competitive segmentation performance, especially with minuscule neural architecture model size, i.e., 0.61M that is superior to U-Net (7.76 M) and UNet++ (9.04 M).

Graph neural architecture search (NAS) has gained great popularity in automatically designing powerful graph neural networks (GNNs) with superior learning abilities, significantly relieving human effort and expertise reliance. Despite the advanced performance of automated learning, existing graph NAS models mainly work on single-relational graphs, while the widespread multi-relational graphs in real-world applications, are not well addressed. Moreover, current search spaces of automated GNNs are generally coarse-grained by simply integrating typical GNN layers and hyper-parameters, resulting in severe limitations on search capacities and scopes for creating innovative GNN architectures. To tackle the limitations of single-relational setting and coarse-grained search space design in existing graph NAS, in this paper, we propose a novel framework of multi-relational graph neural architecture search, dubbed MR-GNAS, to automatically develop innovative and excellent multi-relational GNN architectures. Specifically, to enlarge search capacities and improve search flexibility, MR-GNAS contains a fine-grained search space that embraces the full-pipe multi-relational message passing schema, enabling expressive architecture search scopes. With the well-designed fine-grained search space, MR-GNAS constructs a relation-aware supernet with a tree topology, to jointly learn discriminative node and relation representations. By searching with a gradient-based strategy in the supernet, the proposed MR-GNAS could derive excellent multi-relational GNN architectures in multi-relational graph analysis. Extensive experiments on entity classification and link prediction tasks over multi-relational graphs illustrate the effectiveness and superiority of the proposed method.

Molecular property prediction has achieved promising improvement for accelerating drug development with machine learning models. The emergence of graph neural networks especially benefits the discriminative representation learning of molecular graph data, which has become the key challenge of molecular property prediction. However, most of the existing works extract either graph features or sequence features of molecules, while the significant information from both graph and sequence representations is not well discovered and utilized. In this paper, we propose a Joint Graph-Sequence framework, JointGS, for learning high-quality molecular property representations by jointly capturing information from both graph and sequence molecular data. Specifically, JointGS contains a sequence encoder and a graph encoder working in parallel for learning sequence-level and graph-level molecular embeddings, respectively. Moreover, an attentional feature fusion mechanism is presented to better aggregate graph-sequence molecular embeddings. Extensive experiments demonstrate that the proposed JointGS can achieve superior molecular property prediction performance, especially in the SARS-CoV dataset for screening potential molecules benefiting the COVID-19 drug development.

For many real-world multimedia applications, data are often described by multiple views. Therefore, multi-view learning researches are of great significance. Traditional multi-view clustering methods assume that each view has complete data. However, missing data or partial data are more common in real tasks, which results in partial multi-view learning. Therefore, we propose a novel multi-view clustering method, called Partial Multi-view Subspace Clustering (PMSC), to address the partial multi-view problem. Unlike most existing partial multi-view clustering methods that only learn a new representation of the original data, our method seeks the latent space and performs data reconstruction simultaneously to learn the subspace representation. The learned subspace representation can reveal the underlying subspace structure embedded in original data, leading to a more comprehensive data description. In addition, we enforce the subspace representation to be non-negative, yielding an intuitive weight interpretation among different data. The proposed method can be optimized by the Augmented Lagrange Multiplier (ALM) algorithm. Experiments on one synthetic dataset and four benchmark datasets validate the effectiveness of PMSC under the partial multi-view scenario.