Out-of-distribution (OOD) detection aims to identify the test examples that do not belong to the distribution of training data. The distance-based methods, which identify OOD examples based on their distances from the centroids of in-distribution (ID) examples, have demonstrated promising OOD detection performance. However, the objectives utilized in prior approaches are typically designed for classification and thus might not yield sufficient discriminative power to distinguish between ID and OOD examples. Therefore, this paper proposes a prototype-based contrastive learning framework for OOD detection, which is termed provable Discriminative Hyperspherical Embedding (DHE). The proposed framework provides a theoretical analysis of inter-class dispersion, which is proved to be fundamental in reducing the false positive rate (FPR) on OOD examples. Based on this, we devise an angular spread loss to achieve the maximal dispersion of the prototypes of different classes prior to training. Subsequently, a prototype-enhanced contrastive loss is introduced to align embeddings of ID examples closely with their corresponding prototypes. In our proposed DHE, the maximal prototype dispersion is theoretically proved, thereby avoiding the pitfalls of local optima commonly encountered by most existing methods. Experimental results demonstrate the effectiveness of our proposed DHE, which showcases a remarkable reduction in FPR95 (i.e., 5.37% on CIFAR-100) and more than doubling the computational efficiency when compared with the state-of-the-art methods.

Vertical Federated Learning (VFL) enables an active party with labeled data to enhance model performance (utility) by collaborating with multiple passive parties that possess auxiliary features corresponding to the same sample identifiers (IDs). Model serving in VFL is vital for real-world, delay-sensitive applications, and it faces two major challenges: 1) robustness against arbitrarily-aligned data and stragglers; and 2) privacy protection, ensuring minimal label leakage to passive parties. Existing methods fail to transfer knowledge among parties to improve robustness in a privacy-preserving way. In this paper, we introduce a privacy-preserving knowledge transfer framework, Complementary Knowledge Distillation (CKD), designed to enhance the robustness and privacy of multi-party VFL systems. Specifically, we formulate a Complementary Label Coding (CLC) objective to encode only complementary label information of the active party's local model for passive parties to learn. Then, CKD selectively transfers the CLC-encoded complementary knowledge 1) from the passive parties to the active party, and 2) among the passive parties themselves. Experimental results on four real-world datasets demonstrate that CKD outperforms existing approaches in terms of robustness against arbitrarily-aligned data, while also minimizing label privacy leakage.

Federated learning empowers privacy-preserving, multi-party secure model training without the necessity of sharing raw data. In recent years, knowledge distillation has emerged as a promising solution to address the significant challenge of model heterogeneity within federated learning. However, current research often overlooks the potential threats posed by Byzantine attacks, which can significantly compromise the security of federated distillation. Previous work on Byzantine attacks has been primarily focused on manipulating local gradients to compromise global model, lacking attacks on logits in knowledge distillation scenarios. In this paper, we introduce two innovative attacks, shedding light on the inherent risks in federated distillation. The proposed attacks include a top-k attack, which perturbs the top k values of logits in each column, and an impersonation attack, which emulates knowledge significantly deviating from the norm. To counter such attacks, we propose a robust aggregation strategy-FedTGD (Federated Top Guard Distillation), designed to ensure robust distillation with heterogeneous models. Specifically, FedTGD incorporates Density-Based Spatial Clustering of Applications with Noise (DBSCAN) and maximum cosine similarity on top-k values of logits to select benign knowledge. Experimental evaluations conducted on FEMNIST and CIFAR100 datasets, considering scenarios for both IID and Non-IID, reveal that top-k attack results in a substantial 27.16% accuracy reduction for FedMD. In contrast, our aggregation method shows a marginal 0.7% accuracy decrease under top-k attacks, outperforming state-of-the-art baselines.

Accurate Traffic Flow Prediction (TFP) is crucial for enhancing the efficiency and safety of transportation systems, so it has attracted intensive researches by exploiting spatial-temporal dependencies within road networks. However, existing works only consider the case of centralized data collection with all traffic data observed, which may raise privacy concerns as each region of a city may have its own traffic administration department and the traffic data is not allowed to distribute. Therefore, this paper proposes to use Federated Learning (FL) to address this issue by allowing all clients (i.e., traffic administration departments in all regions in our problem) to collaboratively train TFP models without exchanging raw data, thereby offering a solution in maintaining data privacy. Nevertheless, most existing FL methods aim to learn a global model that performs well universally, so they cannot well handle the non-Independent and Identically Distributed (non-IID) traffic data naturally over different regions. To cope with this problem, this paper develops a new FL framework termed “personalized Federated learning with Traffic Pattern Sharing” (FedTPS) to solve federated TFP problem. Our FedTPS critically exploits the underlying common traffic patterns (e.g., morning and evening rush hours) shared across different city regions and meanwhile maintaining the region-specific data characteristics in a personalized FL manner. Specifically, to extract the common traffic patterns, we decompose the traffic data in each client via using discrete wavelet transform, where the low-frequency components uncover the stable traffic dynamics of different regions and thus can be considered as the common traffic patterns. These common patterns are then shared among different clients through traffic pattern repositories on the server side to aid the global collaborative traffic flow modeling. Moreover, the model components capturing spatial-temporal dependencies in traffic data are retained for local training, thereby enabling personalized learning based on regional characteristics. Intensive experiments on four real-world traffic datasets firmly demonstrate the superiority of our proposed FedTPS over other compared typical FL methods in terms of various estimation errors.

In real-world hyperspectral image (HSI) classification, the limited annotated examples usually lead to the insufficiently trained classifier, which further generates low classification accuracy. To overcome this challenge, Domain Adaptation (DA) methods have been developed to transfer learnable knowledge from the external HSIs with sufficient labeled examples (i.e., the source domain) to the interested HSI with scarce labeled examples (i.e., the target domain). Conventional DA approaches often pseudo-label the examples with high classification confidence and then incorporate them in the training process. However, due to the significant domain gap, relying solely on the confident examples may not be adequate to achieve satisfactory performance. Therefore, this paper proposes an Interactive Easy-to-Hard Domain Adaptation method (IEH-DA) to arrange the adaptation process so that the “easy” examples are adapted ahead of the “hard” ones. In an early stage, the easy examples with high pseudo-labeling confidence are selected for the adversarial learning based DA. In a later stage, the “hard” examples with high informativity are further selected, and they are interactively labeled by human expert to provide accurate supervision information for adaptation. As a result, the examples in target domain are used in an easy-to-hard way, which forms a curriculum sequence for orderly model training. Extensive experiments conducted on typical public datasets demonstrate that IEH-DA outperforms other state-of-the-art DA methods for HSI classification.

Contrastive learning (CL) is a prominent technique for self-supervised representation learning, which aims to contrast semantically similar (i.e., positive) and dissimilar (i.e., negative) pairs of examples under different augmented views. Recently, CL has provided unprecedented potential for learning expressive graph representations without external supervision. In graph CL, the negative nodes are typically uniformly sampled from augmented views to formulate the contrastive objective. However, this uniform negative sampling strategy limits the expressive power of contrastive models. To be specific, not all the negative nodes can provide sufficiently meaningful knowledge for effective contrastive representation learning. In addition, the negative nodes that are semantically similar to the anchor are undesirably repelled from it, leading to degraded model performance. To address these limitations, in this article, we devise an adaptive sampling strategy termed "AdaS. " The proposed AdaS framework can be trained to adaptively encode the importance of different negative nodes, so as to encourage learning from the most informative graph nodes. Meanwhile, an auxiliary polarization regularizer is proposed to suppress the adverse impacts of the false negatives and enhance the discrimination ability of AdaS. The experimental results on a variety of real-world datasets firmly verify the effectiveness of our AdaS in improving the performance of graph CL.

Cross-platform recommendation aims to improve recommendation accuracy by gathering heterogeneous features from different platforms. However, such cross-silo collaborations between platforms are restricted by increasingly stringent privacy protection regulations, thus data cannot be aggregated for training. Federated learning (FL) is a practical solution to deal with the data silo problem in recommendation scenarios. Existing cross-silo FL methods transmit model information to collaboratively build a global model by leveraging the data of overlapped users. However, in reality, the number of overlapped users is often very small, thus largely limiting the performance of such approaches. Moreover, transmitting model information during training requires high communication costs and may cause serious privacy leakage. In this paper, we propose a novel privacy-preserving double distillation framework named FedPDD for cross-silo federated recommendation, which efficiently transfers knowledge when overlapped users are limited. Specifically, our double distillation strategy enables local models to learn not only explicit knowledge from the other party but also implicit knowledge from its past predictions. Moreover, to ensure privacy and high efficiency, we employ an offline training scheme to reduce communication needs and privacy leakage risk. In addition, we adopt differential privacy to further protect the transmitted information. The experiments on two real-world recommendation datasets, HetRec-MovieLens and Criteo, demonstrate the effectiveness of FedPDD compared to the state-of-the-art approaches.

Recently, graph convolutional network (GCN) has been widely used in hyperspectral image (HSI) classification due to its satisfactory performance. However, the number of labeled pixels is very limited in HSI, and thus, the available supervision information is usually insufficient, which will inevitably degrade the representation ability of most existing GCN-based methods. To enhance the feature representation ability, in this article, a GCN model with contrastive learning is proposed to explore the supervision signals contained in both spectral information and spatial relations, which is termed contrastive GCN (ConGCN), for HSI classification. First, in order to mine sufficient supervision signals from spectral information, a semisupervised contrastive loss function is utilized to maximize the agreement between different views of the same node or the nodes from the same land cover category. Second, to extract the precious yet implicit spatial relations in HSI, a graph generative loss function is leveraged to explore supplementary supervision signals contained in the graph topology. In addition, an adaptive graph augmentation technique is designed to flexibly incorporate the spectral–spatial priors of HSI, which helps facilitate the subsequent contrastive representation learning. The extensive experimental results on six typical benchmark datasets firmly demonstrate the effectiveness of the proposed ConGCN in both qualitative and quantitative aspects.

Recently, graph convolutional network (GCN) has progressed significantly and gained increasing attention in hyperspectral image (HSI) classification due to its impressive representation power. However, existing GCN-based methods do not give full consideration to the multiscale spatial information, since the convolution operations are governed by fixed neighborhood. As a result, their performances can be limited, particularly in the regions with diverse land cover appearances. In this article, we develop a new dual interactive GCN (DIGCN) which introduces the dual GCN branches to capture spatial information at different scales. More significantly, the dual interactive module is embedded across the GCN branches, so that the correlation of multiscale spatial information can be leveraged to refine the graph information. To be concrete, the edge information contained in one GCN branch can be refined by incorporating the feature representations from the other branch. Analogously, improved feature representations can be generated in one GCN branch by fusing the edge information from the other branch. As such, the refined graph information can help enhance the representation power of the model. Furthermore, to avoid the negative effects of the manually constructed graph, our proposed model adaptively learns a discriminative region-induced graph, which also accelerates the convolution operation. We comprehensively evaluate the proposed method on four commonly used HSI benchmark data sets, and the state-of-the-art results can be achieved when compared with several typical HSI classification methods.

Acquiring labeled training examples for hyperspectral images (HSI) is an expensive task, and even labeling one more pixel requires a real-time field survey of tens of square meters. Therefore, it is highly demanded to achieve satisfactory accuracy for an HSI classification method when the number of labeled examples is extremely limited. However, most of the existing methods lack the ability to handle extremely sparse labeled data. To overcome this issue, we propose a novel graph-based framework for HSI classification, termed “dynamic spectral–spatial Poisson learning” (DSSPL). Specifically, three measures are used to enable the proposed model suitable for the situation of extremely limited labeled data. First, Poisson learning (PL) is adopted for predicting labels on a graph, as it can prevent undesirable constant output labels of traditional label propagation methods and generate more informative label determinations. Second, spectral and spatial graphs are constructed from various features and fused to build a spectral–spatial graph, which exploits comprehensive connective relationships among pixels. Third, in each iteration, the fused graph is dynamically updated by feeding back the up-to-date label information generated by each iteration. The feedback strategy progressively refines the fused graph, and the propagation on the updated graph in turn improves output labels iteratively. Intensive experimental results on three public datasets demonstrate that the proposed DSSPL significantly outperforms other state-of-the-art HSI classification methods when very few pixels (e.g., 3, 5, or 10 of each class) are labeled.

Graph-based Semi-Supervised Learning (SSL) aims to transfer the labels of a handful of labeled data to the remaining massive unlabeled data via a graph. As one of the most popular graph-based SSL approaches, the recently proposed Graph Convolutional Networks (GCNs) have gained remarkable progress by combining the sound expressiveness of neural networks with graph structure. Nevertheless, the existing graph-based methods do not directly address the core problem of SSL, \emph{i.e.}, the shortage of supervision, and thus their performances are still very limited. To accommodate this issue, this paper presents a novel GCN-based SSL algorithm which aims to enrich the supervision signals by utilizing both data similarities and graph structure. Firstly, by designing a semi-supervised contrastive loss, the improved node representations can be generated via maximizing the agreement between different views of the same data or the data from the same class. Therefore, the rich unlabeled data and the scarce yet valuable labeled data can jointly provide abundant supervision information for learning discriminative node representations, which helps improve the subsequent classification result. Secondly, the underlying determinative relationship between the input graph topology and data features is extracted as supplementary supervision signals for SSL via using a graph generative loss related to input features. Intensive experimental results on a variety of real-world datasets firmly verify the effectiveness of our algorithm when compared with other state-of-the-art methods.

Graph Neural Networks (GNNs) have achieved remarkable performance in the task of semi-supervised node classification. However, most existing GNN models require sufficient labeled data for effective network training. Their performance can be seriously degraded when labels are extremely limited. To address this issue, we propose a new framework termed Contrastive Graph Poisson Networks (CGPN) for node classification under extremely limited labeled data. Specifically, our CGPN derives from variational inference; integrates a newly designed Graph Poisson Network (GPN) to effectively propagate the limited labels to the entire graph and a normal GNN, such as Graph Attention Network, that flexibly guides the propagation of GPN; applies a contrastive objective to further exploit the supervision information from the learning process of GPN and GNN models. Essentially, our CGPN can enhance the learning performance of GNNs under extremely limited labels by contrastively propagating the limited labels to the entire graph. We conducted extensive experiments on different types of datasets to demonstrate the superiority of CGPN.

In hyperspectral image (HSI) classification, spatial context has demonstrated its significance in achieving promising performance. However, conventional spatial context-based methods simply assume that spatially neighboring pixels should correspond to the same land-cover class, so they often fail to correctly discover the contextual relations among pixels in complex situations, and thus leading to imperfect classification results on some irregular or inhomogeneous regions such as class boundaries. To address this deficiency, we develop a new HSI classification method based on the recently proposed graph convolutional network (GCN), as it can flexibly encode the relations among arbitrarily structured non-Euclidean data. Different from traditional GCN, there are two novel strategies adopted by our method to further exploit the contextual relations for accurate HSI classification. First, since the receptive field of traditional GCN is often limited to fairly small neighborhood, we proposed to capture long-range contextual relations in HSI by performing successive graph convolutions on a learned region-induced graph which is transformed from the original 2-D image grids. Second, we refine the graph edge weight and the connective relationships among image regions simultaneously by learning the improved similarity measurement and the “edge filter,” so that the graph can be gradually refined to adapt to the representations generated by each graph convolutional layer. Such updated graph will in turn result in faithful region representations, and vice versa. The experiments carried out on four real-world benchmark data sets demonstrate the effectiveness of the proposed method.

Estimating the Ratio of Edge-Users (REU) is an important issue in mobile networks, as it helps the subsequent adjustment of loads in different cells. However, existing approaches usually determine the REU manually, which are experience-dependent and labor-intensive, and thus the estimated REU might be imprecise. Considering the inherited graph structure of mobile networks, in this paper, we utilize a graph-based deep learning method for automatic REU estimation, where the practical cells are deemed as nodes and the load switchings among them constitute edges. Concretely, Graph Attention Network (GAT) is employed as the backbone of our method due to its impressive generalizability in dealing with networked data. Nevertheless, conventional GAT cannot make full use of the information in mobile networks, since it only incorporates node features to infer the pairwise importance and conduct graph convolutions, while the edge features that are actually critical in our problem are disregarded. To accommodate this issue, we propose an Edge-Aware Graph Attention Network (EAGAT), which is able to fuse the node features and edge features for REU estimation. Extensive experimental results on two real-world mobile network datasets demonstrate the superiority of our EAGAT approach to several state-of-the-art methods.

Deep neural networks (DNNs) are recently found to be vulnerable to JPEG compression artifacts, which distort the feature representations of DNNs leading to serious accuracy degradation. Most existing training methods which aim to address this problem add compressed images to the training data to enhance the robustness of DNNs. However, their improvements are limited since these methods usually regard the compressed images as new training samples instead of distorted samples. The feature distortions between the raw images and the compressed images are not investigated. In this work, we propose a new training method, called Feature Consistency Training, that is designed to minimize the feature distortions caused by JPEG artifacts. At each training iteration, we simultaneously input a raw image and its compressed version with a randomly sampled quality into a DNN model and extract the features from the internal layers. By adding feature consistency constraint to the objective function, the feature distortions in the representation space are minimized in order to learn robust filters. Besides, we present a residual mapping block which takes the quality factor of the compressed image as an additional information to further reduce the feature distortion. Extensive experiments demonstrate that our method outperforms several existed training methods on JPEG compressed images. Furthermore, DNN models trained by our method are found to be more robust to unseen distortions.

Convolutional neural network (CNN) has demonstrated impressive ability to represent hyperspectral images and to achieve promising results in hyperspectral image classification. However, traditional CNN models can only operate convolution on regular square image regions with fixed size and weights, and thus, they cannot universally adapt to the distinct local regions with various object distributions and geometric appearances. Therefore, their classification performances are still to be improved, especially in class boundaries. To alleviate this shortcoming, we consider employing the recently proposed graph convolutional network (GCN) for hyperspectral image classification, as it can conduct the convolution on arbitrarily structured non-Euclidean data and is applicable to the irregular image regions represented by graph topological information. Different from the commonly used GCN models that work on a fixed graph, we enable the graph to be dynamically updated along with the graph convolution process so that these two steps can be benefited from each other to gradually produce the discriminative embedded features as well as a refined graph. Moreover, to comprehensively deploy the multiscale information inherited by hyperspectral images, we establish multiple input graphs with different neighborhood scales to extensively exploit the diversified spectral-spatial correlations at multiple scales. Therefore, our method is termed multiscale dynamic GCN (MDGCN). The experimental results on three typical benchmark data sets firmly demonstrate the superiority of the proposed MDGCN to other state-of-the-art methods in both qualitative and quantitative aspects.

Head pose estimation has attracted immense research interest recently, as its inherent information significantly improves the performance of face-related applications such as face alignment and face recognition. In this paper, we conduct an in-depth study of head pose estimation and present a multiregression loss function, an L2 regression loss combined with an ordinal regression loss, to train a convolutional neural network (CNN) that is dedicated to estimating head poses from RGB images without depth information. The ordinal regression loss is utilized to address the nonstationary property observed as the facial features change with respect to different head pose angles and learn robust features. The L2 regression loss leverages these features to provide precise angle predictions for input images. To avoid the ambiguity problem in the commonly used Euler angle representation, we further formulate the head pose estimation problem in quaternions. Our quaternion-based multiregression loss method achieves state-of-the-art performance on the AFLW2000, AFLW test set, and AFW datasets and is closing the gap with methods that utilize depth information on the BIWI dataset.

In this paper, we propose Confidence Network (ConfNet) which not only makes predictions on input images but also generates a confidence score that estimates the probability of correctness of each prediction. Furthermore, Confidence Loss is proposed to make ConfNet automatically learn confidence scores in the training phase. The experiments on two public datasets show that the confidence scores generated by ConfNet are highly correlated with the model accuracy and outperforms two related methods. When stacking two ConfNets in a cascade structure, 3.8x computational cost can be saved compared to the single state-of-the-art model with only 0.1 % increase of error rate.

Privacy issues in Location-Based Services (LBSs) have gained tremendous attentions in literature over recent years. Existing approaches always fail to provide dual privacy protection on both user's location and point of interest (POI), incur endurable system overhead, and produce high quality of services, simultaneously. To address these problems, we propose a time obfuscation-based scheme, termed TOP-privacy, which carefully generates and sends some dummy queries at leisure time to confuse adversaries with some background information. TOP-privacy employs a dummy query generation algorithm, which includes a dummy location selection module and a classified POI pool construction module. It first selects some location candidates with similar location distribution with the real user's, and then determines the optimal POI to construct the dummy query based on the similarity to the user's real POI. Security analysis and evaluation results indicate its effectiveness and efficiency.

In this paper, a novel stochastic (or online) training algorithm for neural networks, named parameter incremental learning (PIL) algorithm, is proposed and developed. The main idea of the PIL strategy is that the learning algorithm should not only adapt to the newly presented input-output training pattern by adjusting parameters, but also preserve the prior results. A general PIL algorithm for feedforward neural networks is accordingly presented as the first-order approximate solution to an optimization problem, where the performance index is the combination of proper measures of preservation and adaptation. The PIL algorithms for the multilayer perceptron (MLP) are subsequently derived. Numerical studies show that for all the three benchmark problems used in this paper the PIL algorithm for MLP is measurably superior to the standard online backpropagation (BP) algorithm and the stochastic diagonal Levenberg-Marquardt (SDLM) algorithm in terms of the convergence speed and accuracy. Other appealing features of the PIL algorithm are that it is computationally as simple as the BP algorithm, and as easy to use as the BP algorithm. It, therefore, can be applied, with better performance, to any situations where the standard online BP algorithm is applicable.