Related papers: Author Name Disambiguation on Heterogeneous Inform…

Generating multiple categories of texts is a challenging task and draws more and more attention. Since generative adversarial nets (GANs) have shown competitive results on general text generation, they are extended for category text…

We study how to generate captions that are not only accurate in describing an image but also discriminative across different images. The problem is both fundamental and interesting, as most machine-generated captions, despite phenomenal…

Generative adversarial networks are generative models that are capable of replicating the implicit probability distribution of the input data with high accuracy. Traditionally, GANs consist of a Generator and a Discriminator which interact…

The disambiguation of author names is an important and challenging task in bibliometrics. We propose an approach that relies on an external source of information for selecting and validating clusters of publications identified through an…

Semantic segmentation has been a long standing challenging task in computer vision. It aims at assigning a label to each image pixel and needs significant number of pixellevel annotated data, which is often unavailable. To address this…

Despite the potential benefits of data augmentation for mitigating the data insufficiency, traditional augmentation methods primarily rely on the prior intra-domain knowledge. On the other hand, advanced generative adversarial networks…

Cross-modal hashing aims to map heterogeneous multimedia data into a common Hamming space, which can realize fast and flexible retrieval across different modalities. Supervised cross-modal hashing methods have achieved considerable progress…

We present an approach for generating clarification questions with the goal of eliciting new information that would make the given textual context more complete. We propose that modeling hypothetical answers (to clarification questions) as…

Adversarial purification using generative models demonstrates strong adversarial defense performance. These methods are classifier and attack-agnostic, making them versatile but often computationally intensive. Recent strides in diffusion…

With the increasing size of digital libraries it has become a challenge to identify author names correctly. The situation becomes more critical when different persons share the same name (homonym problem) or when the names of authors are…

A fundamental feature of human intelligence is the ability to infer high-level abstractions from low-level sensory data. An essential component of such inference is the ability to discover modularized generative mechanisms. Despite many…

Generative Adversarial Networks (GANs) have been studied in text generation to tackle the exposure bias problem. Despite their remarkable development, they adopt autoregressive structures so suffering from high latency in both training and…

Disentangled Representation Learning aims to improve the explainability of deep learning methods by training a data encoder that identifies semantically meaningful latent variables in the data generation process. Nevertheless, there is no…

Recently, deep learning has made significant progress in the task of sequential recommendation. Existing neural sequential recommenders typically adopt a generative way trained with Maximum Likelihood Estimation (MLE). When context…

Generative Adversarial Networks (GANs) have shown great promise in modeling high dimensional data. The learning objective of GANs usually minimizes some measure discrepancy, \textit{e.g.}, $f$-divergence~($f$-GANs) or Integral Probability…

Recent advances in natural language processing have enabled powerful privacy-invasive authorship attribution. To counter authorship attribution, researchers have proposed a variety of rule-based and learning-based text obfuscation…

Auto-regressive text generation models usually focus on local fluency, and may cause inconsistent semantic meaning in long text generation. Further, automatically generating words with similar semantics is challenging, and hand-crafted…

We propose MAD-GAN, an intuitive generalization to the Generative Adversarial Networks (GANs) and its conditional variants to address the well known problem of mode collapse. First, MAD-GAN is a multi-agent GAN architecture incorporating…

The two key players in Generative Adversarial Networks (GANs), the discriminator and generator, are usually parameterized as deep neural networks (DNNs). On many generative tasks, GANs achieve state-of-the-art performance but are often…

Heterogeneous information networks (HINs) can be used to model various real-world systems. As HINs consist of multiple types of nodes, edges, and node features, it is nontrivial to directly apply graph neural network (GNN) techniques in…