Jia cai

Bo Pang, Yifan Zhang, Yaoyi Li et al.

In this paper, we propose a genuine group-level contrastive visual representation learning method whose linear evaluation performance on ImageNet surpasses the vanilla supervised learning. Two mainstream unsupervised learning schemes are the instance-level contrastive framework and clustering-based schemes. The former adopts the extremely fine-grained instance-level discrimination whose supervisory signal is not efficient due to the false negatives. Though the latter solves this, they commonly come with some restrictions affecting the performance. To integrate their advantages, we design the SMoG method. SMoG follows the framework of contrastive learning but replaces the contrastive unit from instance to group, mimicking clustering-based methods. To achieve this, we propose the momentum grouping scheme which synchronously conducts feature grouping with representation learning. In this way, SMoG solves the problem of supervisory signal hysteresis which the clustering-based method usually faces, and reduces the false negatives of instance contrastive methods. We conduct exhaustive experiments to show that SMoG works well on both CNN and Transformer backbones. Results prove that SMoG has surpassed the current SOTA unsupervised representation learning methods. Moreover, its linear evaluation results surpass the performances obtained by vanilla supervised learning and the representation can be well transferred to downstream tasks.

Mengzhu Chen, Haodong Yang, Jia Cai et al.

Retrieval-Augmented Generation (RAG) systems critically depend on how external knowledge is segmented, structured, and retrieved. Most existing approaches either retrieve fixed-length text chunks, which fragments discourse context, or commit to a single structured index (e.g., a knowledge graph or hypergraph), which hard-codes one relational granularity. This often yields brittle retrieval when queries require different forms of evidence, such as local binary relations, higher-order interactions, or broader document-grounded context. We propose \textbf{FlexStructRAG}, a flexible structure-aware RAG framework that supports \emph{multi-granular, query-adaptive retrieval} over heterogeneous knowledge representations. FlexStructRAG jointly constructs (i) a knowledge graph for binary relations, (ii) a knowledge hypergraph for n-ary relations, and (iii) structure-aware semantic clusters that aggregate relational evidence into document-grounded context units. To reduce semantic fragmentation induced by uniform chunking, we introduce dynamic partitioning and a truncated sliding-window extraction mechanism that incorporates bounded contextual dependencies during knowledge construction. At inference time, FlexStructRAG enables entity-, edge-, hyperedge-, and cluster-level retrieval, which can be flexibly combined to supply generation with relationally and contextually aligned evidence. Experiments on the UltraDomain benchmark across four domains show that FlexStructRAG improves semantic evaluation over strong RAG baselines. Ablation and sensitivity analysis further demonstrate the necessity of multi-granular relational retrieval and structure-aware clustering.

Zihao Chen, Zhentao Lin, Bi Zeng et al.

To ensure the reliable operation of speech systems across diverse environments, noise addition methods have emerged as the standard solution.However, existing methods offer limited coverage of real-world scenes and depend on pre-existing noise libraries and scene metadata.This paper presents prompt-based Dynamic Generative Scene-based Noise Addition (DGSNA), a novel approach driven by generative language models that integrates Dynamic Generation of Scene-based Information (DGSI) with Scene-based Noise Addition for Speech (SNAS).The DGSI module, with a BET (Background, Examples, Task) prompt framework, dynamically generates logic-compliant scene-based information, including scene dimensions, sound sources, and microphone positions, thereby addressing the challenges of scene enumeration and detailed description.Complementing this, the SNAS module employs a Time-Frequency Diffusion-based (TFD) Text-to-Audio model to synthesize scene-specific noise. By integrating this noise with clean speech via Room Impulse Response (RIR) filters, the module streamlines the traditionally labor-intensive process of replicating diverse acoustic environments.Experimental results show that DGSNA significantly enhances the robustness of speech recognition and keyword spotting models, achieving relative improvements of up to 11.32\%. Furthermore, DGSNA is highly compatible with existing noise addition techniques. Our implementation and demonstrations are available at https://dgsna.github.io.

Wenjie Liang, Ranhui Yan, Jia Cai et al.

Graph neural networks (GNNs) are increasingly adopted in industrial graph-based monitoring systems (e.g., Industrial internet of things (IIoT) device graphs, power-grid topology models, and manufacturing communication networks) to support anomaly detection, state estimation, and asset classification. In such settings, an adversary that compromises a small number of edge devices may inject counterfeit nodes (e.g., rogue sensors, virtualized endpoints, or spoofed substations) to bias downstream decisions while evading topology- and homophily-based sanitization. This paper formulates deployment-oriented node-injection attacks under constrained resources and proposes the \emph{Single-Edge Graph Injection Attack} (SEGIA), in which each injected node attaches to the operational graph through a single edge. SEGIA integrates a pruned SGC surrogate, multi-hop neighborhood sampling, and reverse graph convolution-based feature synthesis with a similarity-regularized objective to preserve local homophily and survive edge pruning. Theoretical analysis and extensive evaluations across datasets and defenses show at least $25\%$ higher attack success than representative baselines under substantially smaller edge budgets. These results indicate a system-level risk in industrial GNN deployments and motivate lightweight admission validation and neighborhood-consistency monitoring.

Yifang Xu, Jiahao Cui, Feipeng Cai et al.

We introduce WAM-Flow, a vision-language-action (VLA) model that casts ego-trajectory planning as discrete flow matching over a structured token space. In contrast to autoregressive decoders, WAM-Flow performs fully parallel, bidirectional denoising, enabling coarse-to-fine refinement with a tunable compute-accuracy trade-off. Specifically, the approach combines a metric-aligned numerical tokenizer that preserves scalar geometry via triplet-margin learning, a geometry-aware flow objective and a simulator-guided GRPO alignment that integrates safety, ego progress, and comfort rewards while retaining parallel generation. A multi-stage adaptation converts a pre-trained auto-regressive backbone (Janus-1.5B) from causal decoding to non-causal flow model and strengthens road-scene competence through continued multimodal pretraining. Thanks to the inherent nature of consistency model training and parallel decoding inference, WAM-Flow achieves superior closed-loop performance against autoregressive and diffusion-based VLA baselines, with 1-step inference attaining 89.1 PDMS and 5-step inference reaching 90.3 PDMS on NAVSIM v1 benchmark. These results establish discrete flow matching as a new promising paradigm for end-to-end autonomous driving. The code will be publicly available soon.

Ranhui Yan, Jia cai

Heterogeneous Graph Neural Networks (HGNNs) have exhibited powerful performance in heterogeneous graph learning by aggregating information from various types of nodes and edges. However, existing heterogeneous graph models often struggle to capture long-range information or necessitate stacking numerous layers to learn such dependencies, resulting in high computational complexity and encountering over-smoothing issues. In this paper, we propose a Virtual Nodes based Heterogeneous Graph Convolutional Network (VN-HGCN), which leverages virtual nodes to facilitate enhanced information flow within the graph. Virtual nodes are auxiliary nodes interconnected with all nodes of a specific type in the graph, facilitating efficient aggregation of long-range information across different types of nodes and edges. By incorporating virtual nodes into the graph structure, VN-HGCN achieves effective information aggregation with only $4$ layers. Additionally, we demonstrate that VN-HGCN can serve as a versatile framework that can be seamlessly applied to other HGNN models, showcasing its generalizability. Empirical evaluations validate the effectiveness of VN-HGCN, and extensive experiments conducted on three real-world heterogeneous graph datasets demonstrate the superiority of our model over several state-of-the-art baselines.

Guanglong Xu, Zhensheng Hu, Jia Cai

Zero-shot sketch-based image retrieval (ZSSBIR), as a popular studied branch of computer vision, attracts wide attention recently. Unlike sketch-based image retrieval (SBIR), the main aim of ZSSBIR is to retrieve natural images given free hand-drawn sketches that may not appear during training. Previous approaches used semantic aligned sketch-image pairs or utilized memory expensive fusion layer for projecting the visual information to a low dimensional subspace, which ignores the significant heterogeneous cross-domain discrepancy between highly abstract sketch and relevant image. This may yield poor performance in the training phase. To tackle this issue and overcome this drawback, we propose a Wasserstein distance based cross-modal semantic network (WAD-CMSN) for ZSSBIR. Specifically, it first projects the visual information of each branch (sketch, image) to a common low dimensional semantic subspace via Wasserstein distance in an adversarial training manner. Furthermore, identity matching loss is employed to select useful features, which can not only capture complete semantic knowledge, but also alleviate the over-fitting phenomenon caused by the WAD-CMSN model. Experimental results on the challenging Sketchy (Extended) and TU-Berlin (Extended) datasets indicate the effectiveness of the proposed WAD-CMSN model over several competitors.

Zhilong Xiong, Jia Cai

Graph convolutional networks (GCNs) have achieved remarkable learning ability for dealing with various graph structural data recently. In general, deep GCNs do not work well since graph convolution in conventional GCNs is a special form of Laplacian smoothing, which makes the representation of different nodes indistinguishable. In the literature, multi-scale information was employed in GCNs to enhance the expressive power of GCNs. However, over-smoothing phenomenon as a crucial issue of GCNs remains to be solved and investigated. In this paper, we propose two novel multi-scale GCN frameworks by incorporating self-attention mechanism and multi-scale information into the design of GCNs. Our methods greatly improve the computational efficiency and prediction accuracy of the GCNs model. Extensive experiments on both node classification and graph classification demonstrate the effectiveness over several state-of-the-art GCNs. Notably, the proposed two architectures can efficiently mitigate the over-smoothing problem of GCNs, and the layer of our model can even be increased to $64$.

Jia Cai, Zhilong Xiong, Shaogao Lv

Graph convolutional network (GCN) is a powerful model studied broadly in various graph structural data learning tasks. However, to mitigate the over-smoothing phenomenon, and deal with heterogeneous graph structural data, the design of GCN model remains a crucial issue to be investigated. In this paper, we propose a novel GCN called SStaGCN (Simplified stacking based GCN) by utilizing the ideas of stacking and aggregation, which is an adaptive general framework for tackling heterogeneous graph data. Specifically, we first use the base models of stacking to extract the node features of a graph. Subsequently, aggregation methods such as mean, attention and voting techniques are employed to further enhance the ability of node features extraction. Thereafter, the node features are considered as inputs and fed into vanilla GCN model. Furthermore, theoretical generalization bound analysis of the proposed model is explicitly given. Extensive experiments on $3$ public citation networks and another $3$ heterogeneous tabular data demonstrate the effectiveness and efficiency of the proposed approach over state-of-the-art GCNs. Notably, the proposed SStaGCN can efficiently mitigate the over-smoothing problem of GCN.

Kun Fang, Qinghua Tao, Yingwen Wu et al.

Deep Neural Networks (DNNs) are vulnerable to invisible perturbations on the images generated by adversarial attacks, which raises researches on the adversarial robustness of DNNs. A series of methods represented by the adversarial training and its variants have proven as one of the most effective techniques in enhancing the DNN robustness. Generally, adversarial training focuses on enriching the training data by involving perturbed data. Such data augmentation effect of the involved perturbed data in adversarial training does not contribute to the robustness of DNN itself and usually suffers from clean accuracy drop. Towards the robustness of DNN itself, we in this paper propose a novel defense that aims at augmenting the model in order to learn features that are adaptive to diverse inputs, including adversarial examples. More specifically, to augment the model, multiple paths are embedded into the network, and an orthogonality constraint is imposed on these paths to guarantee the diversity among them. A margin-maximization loss is then designed to further boost such DIversity via Orthogonality (DIO). In this way, the proposed DIO augments the model and enhances the robustness of DNN itself as the learned features can be corrected by these mutually-orthogonal paths. Extensive empirical results on various data sets, structures and attacks verify the stronger adversarial robustness of the proposed DIO utilizing model augmentation. Besides, DIO can also be flexibly combined with different data augmentation techniques (e.g., TRADES and DDPM), further promoting robustness gains.

Jia Cai, Kexin Lv, Junyi Huo et al.

Sparse canonical correlation analysis (CCA) is a useful statistical tool to detect latent information with sparse structures. However, sparse CCA works only for two datasets, i.e., there are only two views or two distinct objects. To overcome this limitation, in this paper, we propose a sparse generalized canonical correlation analysis (GCCA), which could detect the latent relations of multiview data with sparse structures. Moreover, the introduced sparsity could be considered as Laplace prior on the canonical variates. Specifically, we convert the GCCA into a linear system of equations and impose $\ell_1$ minimization penalty for sparsity pursuit. This results in a nonconvex problem on Stiefel manifold, which is difficult to solve. Motivated by Boyd's consensus problem, an algorithm based on distributed alternating iteration approach is developed and theoretical consistency analysis is investigated elaborately under mild conditions. Experiments on several synthetic and real world datasets demonstrate the effectiveness of the proposed algorithm.

Chengjin Sun, Sizhe Chen, Jia Cai et al.

Generative models are popular tools with a wide range of applications. Nevertheless, it is as vulnerable to adversarial samples as classifiers. The existing attack methods mainly focus on generating adversarial examples by adding imperceptible perturbations to input, which leads to wrong result. However, we focus on another aspect of attack, i.e., cheating models by significant changes. The former induces Type II error and the latter causes Type I error. In this paper, we propose Type I attack to generative models such as VAE and GAN. One example given in VAE is that we can change an original image significantly to a meaningless one but their reconstruction results are similar. To implement the Type I attack, we destroy the original one by increasing the distance in input space while keeping the output similar because different inputs may correspond to similar features for the property of deep neural network. Experimental results show that our attack method is effective to generate Type I adversarial examples for generative models on large-scale image datasets.