HCHang Cui

Hang Cui

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Hang Cui has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • GARF+: self-supervised and interpretable data cleaning with sequence generative adversarial networks

    by Jinfeng Peng, Hanghai Cui, Derong Shen, Nan Tang, Yue Kou, Tiezheng Nie, Hang Cui, Ge Yu

  • Open Access

    Unsupervised node clustering via contrastive hard sampling

    by Hang Cui, Tarek Abdelzaher

    This paper introduces a fine-grained contrastive learning scheme for unsupervised node clustering. Previous clustering methods only focus on a small feature set (class-dependent features), which demonstrates explicit clustering characteristics, ignoring the rest of the feature spaces (class-invariant features). This paper exploits class-invariant features via graph contrastive learning to discover additional high-quality features for unsupervised clustering. We formulate a novel node-level fine-grained augmentation framework for self-supervised learning, which iteratively identifies competitive contrastive samples from the whole feature spaces, in the form of positive and negative examples of node relations. While positive examples of node relations are usually expressed as edges in graph homophily, negative examples are implicit without a direct edge. We show, however, that simply sampling nodes beyond the local neighborhood results in less competitive negative pairs, that are less effective for contrastive learning. Inspired by counterfactual augmentation, we instead sample competitive negative node relations by creating virtual nodes that inherit (in a self-supervised fashion) class-invariant features, while altering class-dependent features, creating contrasting pairs that lie closer to the boundary and offering better contrast. Consequently, our experiments demonstrate significant improvements in supervised node clustering tasks on six baselines and six real-world social network datasets.

  • Open Access

    Polarization Detection on Social Networks: dual contrastive objectives for Self-supervision

    by Hang Cui, Tarek Abdelzaher

    Echo chambers and online discourses have become prevalent social phenomena where communities engage in dramatic intra-group confirmations and inter-group hostility. Polarization detection is a rising research topic for detecting and identifying such polarized groups. Previous works on polarization detection primarily focus on hand-crafted features derived from dataset-specific characteristics and prior knowledge, which fail to generalize to other datasets. This paper proposes a unified self-supervised polarization detection framework, outperforming previous methods in unsupervised and semi-supervised polarization detection tasks on various publicly available datasets. Our framework utilizes a dual contrastive objective (DocTra): (1) interaction-level: to contrast between node interactions to extract critical features on interaction patterns, and (2) feature-level: to contrast extracted polarized and invariant features to encourage feature decoupling. Our experiments extensively evaluate our methods again 7 baselines on 7 public datasets, demonstrating significant performance improvements.

  • Open Access

    Virtual Node Generation for Node Classification in Sparsely-Labeled Graphs

    by Hang Cui, Tarek Abdelzaher

    In the broader machine learning literature, data-generation methods demonstrate promising results by generating additional informative training examples via augmenting sparse labels. Such methods are less studied in graphs due to the intricate dependencies among nodes in complex topology structures. This paper presents a novel node generation method that infuses a small set of high-quality synthesized nodes into the graph as additional labeled nodes to optimally expand the propagation of labeled information. By simply infusing additional nodes, the framework is orthogonal to the graph learning and downstream classification techniques, and thus is compatible with most popular graph pre-training (self-supervised learning), semi-supervised learning, and meta-learning methods. The contribution lies in designing the generated node set by solving a novel optimization problem. The optimization places the generated nodes in a manner that: (1) minimizes the classification loss to guarantee training accuracy and (2) maximizes label propagation to low-confidence nodes in the downstream task to ensure high-quality propagation. Theoretically, we show that the above dual optimization maximizes the global confidence of node classification. Our Experiments demonstrate statistically significant performance improvements over 14 baselines on 10 publicly available datasets.

  • Empowering Transformer with Hybrid Matching Knowledge for Entity Matching

    by Wenzhou Dou, Derong Shen, Tiezheng Nie, Yue Kou, Chenchen Sun, Hang Cui, Ge Yu