Publications

A novel Atom-Motif Contrastive Transformer for Molecular Property Prediction.

Recently, Graph Transformer (GT) models have been widely used in the task of Molecular Property Prediction (MPP) due to their high reliability in characterizing the latent relationship among graph nodes (i.e., the atoms in a molecule). However, most existing GT-based methods usually explore the basic interactions between pairwise atoms, and thus they fail to consider the important interactions among critical motifs (e.g., functional groups consisted of several atoms) of molecules. As motifs in a molecule are significant patterns that are of great importance for determining molecular properties (e.g., toxicity and solubility), overlooking motif interactions inevitably hinders the effectiveness of MPP. To address this issue, we propose a novel Atom-Motif Contrastive Transformer (AMCT), which not only explores the atom-level interactions but also considers the motif-level interactions. Since the representations of atoms and motifs for a given molecule are actually two different views of the same instance, they are naturally aligned to generate the self-supervisory signals for model training. Meanwhile, the same motif can exist in different molecules, and hence we also employ the contrastive loss to maximize the representation agreement of identical motifs across different molecules. Finally, in order to clearly identify the motifs that are critical in deciding the properties of each molecule, we further construct a property-aware attention mechanism into our learning framework. Our proposed AMCT is extensively evaluated on ten popular benchmark datasets, and both quantitative and qualitative results firmly demonstrate its effectiveness when compared with the state-of-the-art methods.

A novel Federated method which recovers the inter-client dependency with HIdden global componeNTs (FedHINT).

Current works either fail to capture the missing inter-client dependency or compromise data privacy to recover the inter-client dependency. To address this issue, we propose a novel Federated method which recovers the inter-client dependency with HIdden global componeNTs (FedHINT). We find that the traffic data from different local regions actually contain hidden global components that reflect cross-regional traffic changes. Therefore, our FedHINT aims to extract hidden global components from each client to generate proxy nodes that represent global information, which are then utilized to recover the inter-client dependency. To be specific, we employ an attention module, which is guided by the shared global queries to capture hidden global components from local traffic data, to generate proxy nodes. Subsequently, our FedHINT adaptively learns the correlations between proxy nodes and local nodes through a global encoder. During this process, the global information in proxy nodes compensate for the loss of information from cross-regional nodes, which thereby recovers the missing inter-client dependency.

A novel Graph Federated Learning method via semantic and structural alignment.

Graph Federated Learning (GFL) enables distributed graph representation learning while protecting the privacy of graph data. However, GFL suffers from heterogeneity arising from diverse node features and structural topologies across multiple clients. To address both types of heterogeneity, we propose a novel graph Federated learning method via Semantic and Structural Alignment (FedSSA), which shares the knowledge of both node features and structural topologies. For node feature heterogeneity, we propose a novel variational model to infer class-wise node distributions, so that we can cluster clients based on inferred distributions and construct cluster-level representative distributions. We then minimize the divergence between local and cluster-level distributions to facilitate semantic knowledge sharing. For structural heterogeneity, we employ spectral Graph Neural Networks (GNNs) and propose a spectral energy measure to characterize structural information, so that we can cluster clients based on spectral energy and build cluster-level spectral GNNs. We then align the spectral characteristics of local spectral GNNs with those of cluster-level spectral GNNs to enable structural knowledge sharing. Experiments on six homophilic and five heterophilic graph datasets under both non-overlapping and overlapping partitioning settings demonstrate that FedSSA consistently outperforms eleven state-of-the-art methods.

A novel Graph Federated Learning method by integrally modeling the Inter-Intra Heterogeneity.

We propose a novel method FedIIH, which naturally integrates the inter- and intra- heterogeneity in Graph Federated Learning (GFL). On one hand, our method characterizes the interheterogeneity from a multi-level global perspective, and thus it can properly compute the inter-subgraph similarities based on the whole distribution. On the other hand, it disentangles the subgraph into several latent factors, so that we can further consider the critical intra-heterogeneity. To the best of our knowledge, this is the first time in GFL that combines both inter- and intra- heterogeneity into a unified framework.

A FL framework termed “personalized Federated learning with Traffic Pattern Sharing” (FedTPS) to solve federated Traffic Flow Prediction problem.

Traffic flow prediction plays a critical role in ensuring the efficiency of transportation systems, which has motivated extensive research into capturing spatial-temporal dependencies within road networks. However, most existing approaches depend on centralized data, potentially raising privacy concerns as traffic data is often managed by different traffic administration departments and restricted from distribution. To address this issue, federated learning (FL) allows collaborative model training without exchanging raw data. Nevertheless, traditional FL methods are designed to optimize a model that performs well globally, making them inadequate for handling the naturally non-independent and identically distributed traffic data across different regions. To overcome this limitation, we propose a new framework termed “personalized Federated learning with Traffic Pattern Sharing” (FedTPS), which exploits the sharing of underlying common traffic patterns across regions while preserving region-specific characteristics in a personalized manner. Specifically, discrete wavelet transform is employed to decompose the traffic data and extract low-frequency components in each client that reflect stable traffic dynamics. The clients then learn representative traffic patterns from these stable traffic dynamics and store them in traffic pattern repositories. Afterward, these repositories are shared with a central server, which enables the identification and integration of common traffic patterns to improve global learning. Meanwhile, the model components capturing spatial-temporal dependencies are retained for local training, ensuring adaptation to regionspecific data. Intensive experiments on four real-world traffic datasets firmly demonstrate the superiority of our proposed FedTPS over traditional FL methods across various estimation errors.

A FL framework termed “personalized Federated learning with Traffic Pattern Sharing” (FedTPS) to solve federated Traffic Flow Prediction 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.

We introduce a GCN model with contrastive learning that enhances the feature representation ability for hyperspectral image classification.

To enhance the feature representation ability, in this paper, 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 Graph Convolutional Network (ConGCN), for HSI classification.

We propose a novel and robust two-stream spatial–temporal graph convolutional network (2s-STGCN) for driver drowsiness detection.

In this article, we propose a novel and robust two-stream spatial–temporal graph convolutional network (2s-STGCN) for driver drowsiness detection to solve the above-mentioned challenges. To take advantage of the spatial and temporal features of the input data, we use a facial landmark detection method to extract the driver’s facial landmarks from real-time videos and then obtain the driver drowsiness detection result by 2s-STGCN. Unlike existing methods, our proposed method uses videos rather than consecutive video frames as processing units. This is the first effort to exploit these processing units in the field of driver drowsiness detection. Moreover, the two-stream framework not only models both the spatial and temporal features but also models both the first-order and second-order information simultaneously, thereby notably improving driver drowsiness detection. Extensive experiments have been performed on the yawn detection dataset (YawDD) and the National TsingHua University drowsy driver detection (NTHU-DDD) dataset. The experimental results validate the feasibility of the proposed method. This method achieves an average accuracy of 93.4% on the YawDD dataset and an average accuracy of 92.7% on the evaluation set of the NTHU-DDD dataset.