Browsing by Author "Aggarwal, Charu"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Bridging the Gap between Spatial and Spectral Domains: A Unified Framework for Graph Neural Networks
    Chen, Zhiqian; Chen, Fanglan; Zhang, Lei; Ji, Taoran; Fu, Kaiqun; Zhao, Liang; Chen, Feng; Wu, Lingfei; Aggarwal, Charu; Lu, Chang-Tien (ACM, 2023-10)
    Deep learning's performance has been extensively recognized recently. Graph neural networks (GNNs) are designed to deal with graph-structural data that classical deep learning does not easily manage. Since most GNNs were created using distinct theories, direct comparisons are impossible. Prior research has primarily concentrated on categorizing existing models, with little attention paid to their intrinsic connections. The purpose of this study is to establish a unified framework that integrates GNNs based on spectral graph and approximation theory. The framework incorporates a strong integration between spatial- and spectral-based GNNs while tightly associating approaches that exist within each respective domain.
  • Thumbnail Image
    Self-supervised Short Text Modeling through Auxiliary Context Generation
    Choudhary, Nurendra; Aggarwal, Charu; Subbian, Karthik; Reddy, Chandan K. (ACM, 2022-04-12)
    Short text is ambiguous and often relies predominantly on the domain and context at hand in order to attain semantic relevance. Existing classification models perform poorly on short text due to data sparsity and inadequate context. Auxiliary context, which can often provide sufficient background regarding the domain, is typically available in several application scenarios. While some of the existing works aim to leverage real-world knowledge to enhance short text representations, they fail to place appropriate emphasis on the auxiliary context. Such models do not harness the full potential of the available context in auxiliary sources. To address this challenge, we reformulate short text classification as a dual channel self-supervised learning problem (that leverages auxiliary context) with a generation network and a corresponding prediction model. We propose a self-supervised framework, Pseudo-Auxiliary Context generation network for Short text Modeling (PACS), to comprehensively leverage auxiliary context and is jointly learned with a prediction network in an end-to-end manner. Our PACS model consists of two sub-networks: a Context Generation Network (CGN) that models the auxiliary context?s distribution and a Prediction Network (PN) to map the short text features and auxiliary context distribution to the final class label. Our experimental results on diverse datasets demonstrate that PACS outperforms formidable state-of-the-art baselines. We also demonstrate the performance of our model on cold start scenarios (where contextual information is non-existent) during prediction. Furthermore, we perform interpretability and ablation studies to analyze various representational features captured by our model and the individual contribution of its modules to the overall performance of PACS, respectively.