Search

The huge amount of graph data are published and shared for research and business purposes, which brings great benefit for our society. However, user privacy is badly undermined even though user identity can be anonymized. Graph de-anonymization to identify nodes from an anonymized graph is widely adopted to evaluate users' privacy risks. Most existing de-anonymization methods which are heavily reliant on side information (e.g., seeds, user profiles, community labels) are unrealistic due to the difficulty of collecting this side information. A few graph de-anonymization methods only using structural information, called seed-free methods, have been proposed recently, which mainly take advantage of the local and manual features of nodes while overlooking the global structural information of the graph for de-anonymization. In this paper, a seed-free graph de-anonymization method is proposed, where a deep neural network is adopted to learn features and an adversarial framework is employed for node matching. To be specific, the latent representation of each node is obtained by graph autoencoder. Furthermore, an adversarial learning model is proposed to transform the embedding of the anonymized graph to the latent space of auxiliary graph embedding such that a linear mapping can be derived from a global perspective. Finally, the most similar node pairs in the latent space as the anchor nodes are utilized to launch propagation to de-anonymize all the remaining nodes. The extensive experiments on some real datasets demonstrate that our method is comparative with the seed-based approaches and outperforms the start-of-the-art seed-free method significantly.

Finding a suitable data representation for a specific task has been shown to be crucial in many applications. The success of subspace clustering depends on the assumption that the data can be separated into different subspaces. However, this simple assumption does not always hold since the raw data might not be separable into subspaces. To recover the "clustering-friendly" representation and facilitate the subsequent clustering, we propose a graph filtering approach by which a smooth representation is achieved. Specifically, it injects graph similarity into data features by applying a low-pass filter to extract useful data representations for clustering. Extensive experiments on image and document clustering datasets demonstrate that our method improves upon state-of-the-art subspace clustering techniques. Especially, its comparable performance with deep learning methods emphasizes the effectiveness of the simple graph filtering scheme for many real-world applications. An ablation study shows that graph filtering can remove noise, preserve structure in the image, and increase the separability of classes.

In this paper, we present an attention mechanism scheme to improve the person re-identification task. Inspired by biology, we propose Self Attention Grid (SAG) to discover the most informative parts from a high-resolution image using its internal representation. In particular, given an input image, the proposed model is fed with two copies of the same image and consists of two branches. The upper branch processes the high-resolution image and learns high dimensional feature representation while the lower branch processes the low-resolution image and learns a filtering attention grid. We apply a max filter operation to non-overlapping sub-regions on the high feature representation before element-wise multiplied with the output of the second branch. The feature maps of the second branch are subsequently weighted to reflect the importance of each patch of the grid using a softmax operation. Our attention module helps the network to learn the most discriminative visual features of multiple image regions and is specifically optimized to attend feature representation at different levels. Extensive experiments on three large-scale datasets show that our self-attention mechanism significantly improves the baseline model and outperforms various state-of-art models by a large margin.

In this paper, we propose a new label smoothing regularization scheme for person re-identification. We first use an unsupervised method for discriminative learning representation. We apply a clustering algorithm on the learned feature to partition the training set into k groups of equal variance and derive a shared space for similar images. Secondly, a GAN model is fed with each cluster to produce samples with relatively similar features to the original space. Our method consists of assigning an adaptive smooth label distribution to each generated sample according to their original cluster. To train our model, we define a new objective function which takes into account the generated samples and fine-tuned a CNN baseline using the objective function. Our model learns to exploit the samples generated by the GAN model to boost the performance of the person re-id by improving generalization. Extensive evaluations were conducted on four large-scale datasets to validate the advantage of the proposed model.