GNNs have achieved remarkable performance across a range of tasks, but their reliability under distribution shifts remains a significant challenge. In particular, energy-based OOD detection methods—which compute energy scores from GNN logits—suffer from unstable performance due to a fundamental coupling between the norm and direction of node embeddings. Our analysis reveals that this coupling leads to systematic misclassification of high-norm OOD samples and hinders reliable ID–OOD separation. Interestingly, GNNs also exhibit a desirable inductive bias known as angular clustering, where embeddings of the same class align in direction. Motivated by these observations, we propose GeoEnergy (Geometric Logit Decoupling for Energy-Based OOD Detection), a plug-and-play framework that enforces hyperspherical logit geometry by normalizing class weights while preserving embedding norms. This decoupling yields more structured energy distributions, sharper intra-class alignment, and improved calibration. GeoEnergy can be integrated into existing energy-based GNNs without retraining or architectural modification. Extensive experiments demonstrate that GeoEnergy consistently improves OOD detection performance and confidence reliability across various benchmarks and distribution shifts.

Confidence calibration in Graph Neural Networks (GNNs) aims to align a model's predicted confidence with its actual accuracy. Recent studies have indicated that GNNs exhibit an under-confidence bias, which contrasts the over-confidence bias commonly observed in deep neural networks. However, our deeper investigation into this topic reveals that not all GNNs exhibit this behavior. Upon closer examination of message passing in GNNs, we found a clear link between message aggregation and confidence levels. Specifically, GNNs with extensive message aggregation, often seen in deep architectures or when leveraging large amounts of labeled data, tend to exhibit overconfidence. This overconfidence can be attributed to factors like over-learning and over-smoothing. Conversely, GNNs with fewer layers, known for their balanced message passing and superior node representation, may exhibit under-confidence. To counter these confidence biases, we introduce the Adaptive Unified Label Smoothing (AU-LS) technique. Our experiments show that AU-LS outperforms existing methods, addressing both over and under-confidence in various GNN scenarios.

Robust models must demonstrate strong generalizability, even amid environmental changes. However, the complex variability and noise in real-world data often lead to a pronounced performance gap between the training and testing phases. Researchers have recently introduced test-time-domain adaptation (TTA) to address this challenge. TTA methods primarily adapt source-pretrained models to a target domain using only unlabeled test data. This study found that existing TTA methods consider only the largest logit as a pseudo-label and aim to minimize the entropy of test time predictions. This maximizes the predictive confidence of the model. However, this corresponds to the model being overconfident in the local test scenarios. In response, we introduce a novel confidence-calibration loss function called Calibrated Entropy Test-Time Adaptation (CETA), which considers the model's largest logit and the next-highest-ranked one, aiming to strike a balance between overconfidence and underconfidence. This was achieved by incorporating a sample-wise regularization term. We also provide a theoretical foundation for the proposed loss function. Experimentally, our method outperformed existing strategies on benchmark corruption datasets across multiple models, underscoring the efficacy of our approach.

This paper delves into the confidence calibration in prediction when using Graph Neural Networks (GNNs), which has emerged as a notable challenge in the field. Despite their remarkable capabilities in processing graph-structured data, GNNs are prone to exhibit lower confidence in their predictions than what the actual accuracy warrants. Recent advances attempt to address this by minimizing prediction entropy to enhance confidence levels. However, this method inadvertently risks leading to over-confidence in model predictions. Our investigation in this work reveals that most existing GNN calibration methods predominantly focus on the highest logit, thereby neglecting the entire spectrum of prediction probabilities. To alleviate this limitation, we introduce a novel framework called Balanced Calibrated Graph Neural Network (BCGNN), specifically designed to establish a balanced calibration between over-confidence and under-confidence in GNNs' prediction. To theoretically support our proposed method, we further demonstrate the mechanism of the BCGNN framework in effective confidence calibration and significant trustworthiness improvement in prediction. We conduct extensive experiments to examine the developed framework. The empirical results show our method's superior performance in predictive confidence and trustworthiness, affirming its practical applicability and effectiveness in real-world scenarios.

The security of Deep Neural Networks (DNNs) has proven to be critical for their applicabilities in real-world scenarios. However, DNNs are well-known to be vulnerable against adversarial attacks, such as adding artificially designed imperceptible magnitude perturbation to the benign input. Therefore, adversarial robustness is essential for DNNs to defend against malicious attacks. Stochastic Neural Networks (SNNs) have recently shown effective performance on enhancing adversarial robustness by injecting uncertainty into models. Nevertheless, existing SNNs are still limited for adversarial defense, as their insufficient representation capability from the fixed uncertainty. In this paper, to elevate feature representation capability of SNNs, we propose a novel yet practical stochastic neural network that maximizes feature distribution variance (MFDV-SNN). In addition, we provide theoretical insights to support the adversarial resistance of MFDV, which primarily derived from the stochastic noise we injected into DNNs. Our research demonstrates that by gradually increasing the level of stochastic noise in a DNN, the model naturally becomes more resistant to input perturbations. Since adversarial training is not required, MFDV-SNN does not compromise clean data accuracy and saves up to 7.5 times computation time. Extensive experiments on various attacks demonstrate that MFDV-SNN improves adversarial robustness significantly compared to other methods.

Short videos turn into an important channel for public sharing, as well as they've become a fertile ground for fake news. Fake news video detection is to judge the veracity of news based on its different modal information, such as video, audio, text, image and social context information. Current detection models tend to learn the multimodal dataset biases within spurious correlations between news modalities and veracity labels as shortcuts, rather than learning how to integrate the multimodal information behind them to reason, resulting in seriously degrading their detection and generalization capabilities. To address this issues, we propose a Multimodal Multi-View Debiasing (MMVD) framework, which makes the first attempt to mitigate various multimodal biases for fake news video detection. Inspired by people's misleading situations by multimodal short videos, we summarize three cognitive biases: static, dynamic and social biases. MMVD put forward a multi-view causal reasoning strategy to learn unbiased dependencies within the cognitive biases, thus enhancing the unbiased prediction of multimodal videos. The extensive experimental results show that the MMVD could improve the detection performance of multimodal fake news video. Studies also confirm that our MMVD can mitigate multiple biases on complex real-world scenarios and improve generalization ability of fake news video detection.

Deep Neural Networks (DNNs) are known to be vulnerable to adversarial attacks. Recently, Stochastic Neural Networks (SNNs) have been proposed to enhance adversarial robustness by injecting uncertainty into the models. However, existing SNNs often inspired by intuition and rely on adversarial training, which is computationally costly. To address this issue, we propose a novel SNN called the Weight-based Stochastic Neural Network (WB-SNN), which is based on optimizing an error upper bound of adversarial robustness from the perspective of weight distribution. To the best of our knowledge, we are the first to propose a theoretically guaranteed weight-based stochastic neural network without relying on adversarial training. In comparison to normal adversarial training, our method saves about three times the computation cost. Extensive experiments on various datasets, networks, and adversarial attacks have demonstrated the effectiveness of the proposed method.

The vulnerability of deep learning algorithms to malicious attack has garnered significant attention from researchers in recent years. In order to provide more reliable services for safety-sensitive applications, prior studies have introduced Stochastic Neural Networks (SNNs) as a means of improving adversarial robustness. However, existing SNNs are not designed from the perspective of optimizing the adversarial decision boundary and rely on complex and expensive adversarial training. To find an appropriate decision boundary, we propose a simple and effective stochastic neural network that incorporates a regularization term into the objective function. Our approach maximizes the variance of the feature distribution in low-dimensional space and forces the feature direction to align with the eigenvectors of the covariance matrix. Due to no need of adversarial training, our method requires lower computational cost and does not sacrifice accuracy on normal examples, making it suitable for use with a variety of models. Extensive experiments against various well-known white- and black-box attacks show that our proposed method outperforms state-of-the-art methods.

Despite the great success of Graph Neural Networks (GNNs), the trustworthiness is still lack-explored. A very recent study suggests that GNNs are under-confident on the predictions which is opposite to deep neural networks. In this paper, we investigate why this is the case. We discover that the "shallow" network of GNNs is the central cause. To address this challenge, we propose a novel Graph Calibration Loss (GCL), the first end-to-end calibration method for GNNs, which reshapes the standard Cross Entropy loss and is encouraged to assign up-weights loss to high-confidence examples. Through empirical observation and theoretical justification, we discover the GCL's calibration mechanism is to add a minimal-entropy regulariser to KL-divergence to bring down the entropy of correctly classified samples. To evaluate the effectiveness of the GCL, we train several representative GNNs models which use the GCL as loss function on various citation networks datasets, and further apply the GCL to a self-training framework. Compared to the existed methods, the proposed method achieves state-of-the-art calibration performance on node classification task and even improves the standard classification accuracy in almost all cases.

Stochastic neural network (SNN) has attracted increasing attention in recent years, which benefits several important tasks by modeling samples uncertainly, such as adversarial defense, label noise robustness, and model calibration. The current implementations of existing stochastic neural networks are mainly Gaussian noise injection, e.g., deep Variational Information Bottleneck (VIB) uses fixed Gaussian prior to derive noise injection, simple and effective stochastic neural network (SE-SNN) uses a non-informative Gaussian prior to implement it. However, Gaussian distribution assumption is insufficient to model more complex distributions of data in practical, such as the skewed distribution or multi-modal distribution. In this paper, we relax the strict Gaussian prior assumption, and propose a novel distribution calibrated stochastic neural network (DCSNN) which integrates two successive steps. These two steps are as follows: 1) The trained feature vector is preprocessed to make its feature distribution closer to the Gaussian-like distribution. 2) Gaussian distribution’s mean and variance are used to model the sample’s activation indeterminacy. The experimental results show that, compared with the existing methods, our proposed method can achieve state-of-the-art results in a variety of datasets, backbone architectures and multiple applications.

Class imbalance is a widely existed and challenging problem in real-world applications such as disease diagnosis, fraud detection, network intrusion detection and so on. Due to the scarce of data, it could significantly deteriorate the accuracy of classification. To address this challenge, we propose a novel Imbalanced Data Augmentation Generative Adversarial Networks (GAN) named IDA-GAN as an augmentation tool to deal with the imbalanced dataset. This is a great challenge because it is hard to train a GAN model under this situation. We address this issue by coupling variational autoencoder along with GAN training. In this paper, specifically, we introduce the variational autoencoder to learn the majority and minority class distributions in the latent space, and use the generative model to utilize each class distribution for the subsequent GAN training. The generative model learns useful features to generate target minority-class samples. Compared with the state-of-the-art GAN model, the experimental results demonstrate that our proposed IDA-GAN could generate more diverse minority samples with better qualities, and it could benefits the imbalanced classification task in terms of several widely-used evaluation metrics on five benchmark datasets: MNIST, Fashion-MNIST, SVHN, CIFAR-10 and GTSRB.