DETR-based methods have shown impressive performance in object detection tasks. The original DETR employs one-to-one sparse supervision, resulting in poor supervision capability. Denoising training methods introduce additional noisy queries and train the decoder to reconstruct the ground truth boxes, thereby providing extra supervision and improving training efficiency. However, existing denoising training methods generate additional noisy queries based on random distributions, which are inconsistent with the noise distribution of the one-to-one queries, thus limiting the effectiveness of their supervision. To alleviate this, we propose a novel Sampling DeNoising method (SDN) that includes two key components: Noise Collection Builder and Sampling Query Generator. In the Noise Collection Builder, we continuously collect one-to-one query noise and iteratively update the initial query noise collection, ensuring that its noise distribution is similar to that of one-to-one queries, thereby alleviating the inconsistency. In the Sampling Query Generator, we randomly sample from the Noise Collection Builder and introduce random fluctuations to enhance the diversity of the noise samples. Meanwhile, we inject hard noise samples into the Sampling Query Generator to improve the decoder’s bounding box refinement ability. Experiments on two datasets demonstrate that the SDN method leads to a significant performance improvement. Our code is available at https://github.com/yimingfy/SDNDETR.

Document-level relation extraction focuses on identifying and extracting entity relationships within unstructured documents. It differs from sentence-level extraction as it involves more complex and longer distances relationship understanding, including interactions among multiple relations across sentences or paragraphs. Furthermore, in long documents, the issue of data imbalance becomes increasingly prominent. To address aforementioned challenges, we introduce a memory-augmented document-level relation extraction method with U-Mamba (MAUM), which integrates Mamba with U-Net to effectively capture long-range dependencies and global contextual information among multi labels and entities. We then adopt the adaptive hinge balance loss function to mitigate the issue of label imbalance. In addition, MAUM enhances memory by integrating the Token Turing Machine to fully exploit the potential of large-scale annotated and distantly-supervised data. Extensive experiments on DocRED and Re-DocRED, two widely used benchmark datasets for document-level relation extraction, reveal that MAUM has achieved comprehensive improvements compared to the existing SOTA model (with an F1 score improvement of over 2.5%). Our code is available at https://github.com/huruqi10/MAUM.

In this work, we investigate the reach-avoid problem of a class of time-varying analytic systems with disturbances described by uncertain parameters. Firstly, by proposing the concepts of maximal and minimal reachable sets, we connect the avoidability and reachability with maximal and minimal reachable sets respectively. Then, for a given disturbance parameter, we introduce the evolution function for exactly describing the reachable set, and find a series representation of this evolution function with its Lie derivatives, which can also be regarded as a series function with respect to the uncertain parameter. Afterward, based on the partial sums of this series, over- and under-approximations of the evolution function are constructed, which can be realized by interval arithmetics with designated precision. Further, we propose sufficient conditions for avoidability and reachability and design a numerical quantifier elimination-based algorithm to verify these conditions; moreover, we improve the algorithm with a time-splitting technique. We implement the algorithms and use some benchmarks with comparisons to show that our methodology is both efficient and promising. Finally, we additionally extend our methodology to deal with systems with complex initial sets and time-dependent switchings. The performance of our extended method for these systems is also shown by four examples with comparisons and discussions.

Accurate nuclei segmentation is fundamental in histology image analysis, playing an essential role in cancer grading and diagnosis. However, this task remains challenging due to variations in staining protocols, heterogeneity among nuclei types, and the densely clustered nature of nuclei. While SAM exhibits zero-shot generalization capabilities in natural image segmentation, its performance degrades when applied to nuclei segmentation in histology images. Existing adaptations of SAM for medical imaging primarily focus on organ or lesion segmentation, which differs substantially from nuclei segmentation due to the unique characteristics of nuclei—specifically, their sparse distribution combined with dense clustering. To address these challenges, we propose Edge-SAN (Segment Any Nuclei with Edge Prompting), an interactive segmentation foundation model specifically designed for nuclei segmentation. Edge-SAN introduces a novel edge prompting method that enhances the delineation of nuclei boundaries, particularly among densely clustered nuclei, by leveraging edge information to improve segmentation accuracy. We evaluate Edge-SAN on 12 diverse datasets in both few-shot and zero-shot scenarios, demonstrating its effectiveness as a foundation model for nuclei segmentation, achieving 66.81% AJI and 73.13% DSC—improvements of 16.33% and 15.48% over SAM-Med2D, respectively. The code is available at https://github.com/deep-geo/Edge-SAN.

In this work, we investigate the reach-avoid problem of a class of time-varying analytic systems with disturbances described by uncertain parameters. Firstly, by proposing the concepts of maximal and minimal reachable sets, we connect the avoidability and reachability with maximal and minimal reachable sets respectively. Then, for a given disturbance parameter, we introduce the evolution function for exactly describing the reachable set, and find a series representation of this evolution function with its Lie derivatives, which can also be regarded as a series function w.r.t. the uncertain parameter. Afterward, based on the partial sums of this series, over- and under-approximations of evolution function are constructed, which can be realized by interval arithmetics with designated precision. Further, we propose sufficient conditions for avoidability and reachability and design a numerical quantifier elimination based algorithm to verify these conditions; moreover, we improve the algorithm with a time-splitting technique. Finally, we implement the algorithm and use some benchmarks with comparisons to show that our methodology is both efficient and promising.

Neighborhood aggregation algorithms like spectral graph convolutional networks (GCNs) formulate graph convolutions as a symmetric Laplacian smoothing operation to aggregate the feature information of one node with that of its neighbors. While they have achieved great success in semi-supervised node classification on graphs, current approaches suffer from the over-smoothing problem when the depth of the neural networks increases, which always leads to a noticeable degradation of performance. To solve this problem, we present graph convolutional ladder-shape networks (GCLN), a novel graph neural network architecture that transmits messages from shallow layers to deeper layers to overcome the over-smoothing problem and dramatically extend the scale of the neural networks with improved performance. We have validated the effectiveness of proposed GCLN at a node-wise level with a semi-supervised task (node classification) and an unsupervised task (node clustering), and at a graph-wise level with graph classification by applying a differentiable pooling operation. The proposed GCLN outperforms original GCNs, deep GCNs and other state-of-the-art GCN-based models for all three tasks, which were designed from various perspectives on six real-world benchmark data sets.

Graph embedding aims to transfer a graph into vectors to facilitate subsequent graph-analytics tasks like link prediction and graph clustering. Most approaches on graph embedding focus on preserving the graph structure or minimizing the reconstruction errors for graph data. They have mostly overlooked the embedding distribution of the latent codes, which unfortunately may lead to inferior representation in many cases. In this article, we present a novel adversarially regularized framework for graph embedding. By employing the graph convolutional network as an encoder, our framework embeds the topological information and node content into a vector representation, from which a graph decoder is further built to reconstruct the input graph. The adversarial training principle is applied to enforce our latent codes to match a prior Gaussian or uniform distribution. Based on this framework, we derive two variants of the adversarial models, the adversarially regularized graph autoencoder (ARGA) and its variational version, and adversarially regularized variational graph autoencoder (ARVGA), to learn the graph embedding effectively. We also exploit other potential variations of ARGA and ARVGA to get a deeper understanding of our designs. Experimental results that compared 12 algorithms for link prediction and 20 algorithms for graph clustering validate our solutions.

Graph clustering is a fundamental task which discovers communities or groups in networks. Recent studies have mostly focused on developing deep learning approaches to learn a compact graph embedding, upon which classic clustering methods like k-means or spectral clustering algorithms are applied. These two-step frameworks are difficult to manipulate and usually lead to suboptimal performance, mainly because the graph embedding is not goal-directed, i.e., designed for the specific clustering task. In this paper, we propose a goal-directed deep learning approach, Deep Attentional Embedded Graph Clustering (DAEGC for short). Our method focuses on attributed graphs to sufficiently explore the two sides of information in graphs. By employing an attention network to capture the importance of the neighboring nodes to a target node, our DAEGC algorithm encodes the topological structure and node content in a graph to a compact representation, on which an inner product decoder is trained to reconstruct the graph structure. Furthermore, soft labels from the graph embedding itself are generated to supervise a self-training graph clustering process, which iteratively refines the clustering results. The self-training process is jointly learned and optimized with the graph embedding in a unified framework, to mutually benefit both components. Experimental results compared with state-of-the-art algorithms demonstrate the superiority of our method.

Graphs are ubiquitous for describing and modeling complicated data structures, and graph embedding is an effective solution to learn a mapping from a graph to a low-dimensional vector space while preserving relevant graph characteristics. Most existing graph embedding approaches either embed the topological information and node features separately or learn one regularized embedding with both sources of information, however, they mostly overlook the interdependency between structural characteristics and node features when processing the graph data into the models. Moreover, existing methods only reconstruct the structural characteristics, which are unable to fully leverage the interaction between the topology and the features associated with its nodes during the encoding-decoding procedure. To address the problem, we propose a framework using autoencoder for graph embedding (GED) and its variational version (VEGD). The contribution of our work is two-fold: 1) the proposed frameworks exploit a feature-dependent graph matrix (FGM) to naturally merge the structural characteristics and node features according to their interdependency; and 2) the Graph Convolutional Network (GCN) decoder of the proposed framework reconstructs both structural characteristics and node features, which naturally possesses the interaction between these two sources of information while learning the embedding. We conducted the experiments on three real-world graph datasets such as Cora, Citeseer and PubMed to evaluate our framework and algorithms, and the results outperform baseline methods on both link prediction and graph clustering tasks.

Graph embedding is an effective method to represent graph data in a low dimensional space for graph analytics. Most existing embedding algorithms typically focus on preserving the topological structure or minimizing the reconstruction errors of graph data, but they have mostly ignored the data distribution of the latent codes from the graphs, which often results in inferior embedding in real-world graph data. In this paper, we propose a novel adversarial graph embedding framework for graph data. The framework encodes the topological structure and node content in a graph to a compact representation, on which a decoder is trained to reconstruct the graph structure. Furthermore, the latent representation is enforced to match a prior distribution via an adversarial training scheme. To learn a robust embedding, two variants of adversarial approaches, adversarially regularized graph autoencoder (ARGA) and adversarially regularized variational graph autoencoder (ARVGA), are developed. Experimental studies on real-world graphs validate our design and demonstrate that our algorithms outperform baselines by a wide margin in link prediction, graph clustering, and graph visualization tasks.

Numerous network representation-based algorithms for network classification have emerged in recent years, but many suffer from two limitations. First, they separate the network representation learning and node classification in networks into two steps, which may result in sub-optimal results because the node representation may not fit the classification model well, and vice versa. Second, they are mostly shallow methods that can only capture the linear and simple relationships in the data. In this paper, we propose an effective deep learning model, Graph Ladder Networks (GLN), for node classification in networks. Our model learns a ladder network which unifies the representation learning and network classification into one single framework by exploiting both labeled and unlabeled nodes in a network. To integrate both structure and node content information in the networks, the most recently developed graph convolution network, is further employed. The experiments on the most popular academic network dataset, Citeseer, demonstrate that our approach reaches outstanding performance compared to other state-of-the-art algorithms.

Network representation aims to represent the nodes in a network as continuous and compact vectors, and has attracted much attention in recent years due to its ability to capture complex structure relationships inside networks. However, existing network representation methods are commonly designed for homogeneous information networks where all the nodes (entities) of a network are of the same type, e.g., papers in a citation network. In this paper, we propose a universal network representation approach (UNRA), that represents different types of nodes in heterogeneous information networks in a continuous and common vector space. The UNRA is built on our latest mutually updated neural language module, which simultaneously captures inter-relationship among homogeneous nodes and node-content correlation. Relationships between different types of nodes are also assembled and learned in a unified framework. Experiments validate that the UNRA achieves outstanding performance, compared to six other state-of-the-art algorithms, in node representation, node classification, and network visualization. In node classification, the UNRA achieves a 3% to 132% performance improvement in terms of accuracy.

An enterprise social network (ESN) involves diversified user groups from producers, suppliers, logistics, to end consumers, and users have different scales, broad interests, and various objectives, such as advertising, branding, customer relationship management etc. In addition, such a highly diversified network is also featured with rich content, including recruiting messages, advertisements, news release, customer complains etc. Due to such complex nature, an immediate need is to properly organize a chaotic enterprise social network as functional groups, where each group corresponds to a set of peers with business interactions and common objectives, and further understand the business role of each group, such as their common interests and key features differing from other groups. In this paper, we argue that due to unique characteristics of enterprise social networks, simple clustering for ESN nodes or using existing topic discovery methods cannot effectively discover functional groups and understand their roles. Alternatively, we propose CENFLD, which carries out co-clustering on enterprise social networks for functional group discovery and understanding. CENFLD is a co-factorization based framework which combines network topology structures and rich content information, including interactions between nodes and correlations between node content, to discover functional user groups. Because the number of functional groups is highly data driven and hard to estimate, CENFLD employs a hold-out test principle to find the group number optimally complying with the underlying data. Experiments and comparisons, with state-of-the-art approaches, on 13 real-world enterprise/organizational networks validate the performance of CENFLD.