相关论文: Explanation-Preserving Augmentation for Semi-Super…

This paper studies learning the representations of whole graphs in both unsupervised and semi-supervised scenarios. Graph-level representations are critical in a variety of real-world applications such as predicting the properties of…

Graph contrastive learning (GCL) has been widely used as an effective self-supervised learning method for graph representation learning. However, how to apply adequate and stable graph augmentation to generating proper views for contrastive…

Recent advances in self-supervised learning (SSL) using large models to learn visual representations from natural images are rapidly closing the gap between the results produced by fully supervised learning and those produced by SSL on…

We propose an entity-agnostic representation learning method for handling the problem of inefficient parameter storage costs brought by embedding knowledge graphs. Conventional knowledge graph embedding methods map elements in a knowledge…

Supervised learning techniques have proven their efficacy in many applications with abundant data. However, applying these methods to medical imaging is challenging due to the scarcity of data, given the high acquisition costs and intricate…

Self-supervised entity alignment (EA) aims to link equivalent entities across different knowledge graphs (KGs) without seed alignments. The current SOTA self-supervised EA method draws inspiration from contrastive learning, originally…

Semi-supervised learning (SSL) has tremendous value in practice due to its ability to utilize both labeled data and unlabelled data. An important class of SSL methods is to naturally represent data as graphs such that the label information…

Contrastive learning has been widely applied to graph representation learning, where the view generators play a vital role in generating effective contrastive samples. Most of the existing contrastive learning methods employ pre-defined…

As Graph Neural Networks (GNNs) have been widely used in real-world applications, model explanations are required not only by users but also by legal regulations. However, simultaneously achieving high fidelity and low computational costs…

Graph neural networks (GNNs), and especially message-passing neural networks, excel in various domains such as physics, drug discovery, and molecular modeling. The expressivity of GNNs with respect to their ability to discriminate…

Tremendous breakthroughs have been developed in Semi-Supervised Semantic Segmentation (S4) through contrastive learning. However, due to limited annotations, the guidance on unlabeled images is generated by the model itself, which…

Deep artificial neural networks require a large corpus of training data in order to effectively learn, where collection of such training data is often expensive and laborious. Data augmentation overcomes this issue by artificially inflating…

Graph Retrieval-Augmented Generation (GRAG or Graph RAG) architectures aim to enhance language understanding and generation by leveraging external knowledge. However, effectively capturing and integrating the rich semantic information…

Recently, graph Convolutional Neural Networks (graph CNNs) have been widely used for graph data representation and semi-supervised learning tasks. However, existing graph CNNs generally use a fixed graph which may be not optimal for…

This paper introduces Variable Substitution as a domain-specific graph augmentation technique for graph contrastive learning (GCL) in the context of searching for mathematical formulas. Standard GCL augmentation techniques often distort the…

Traditional Incremental Learning (IL) targets to handle sequential fully-supervised learning problems where novel classes emerge from time to time. However, due to inherent annotation uncertainty and ambiguity, collecting high-quality…

Recent reinforcement learning (RL) approaches have advanced radiology report generation (RRG), yet two core limitations persist: (1) report-level rewards offer limited evidence-grounded guidance for clinical faithfulness; and (2) current…

Graph neural networks (GNNs) have achieved great success in node classification tasks. However, existing GNNs naturally bias towards the majority classes with more labelled data and ignore those minority classes with relatively few labelled…

This paper introduces a cutting-edge method for enhancing recommender systems through the integration of generative self-supervised learning (SSL) with a Residual Graph Transformer. Our approach emphasizes the importance of superior data…

Pre-trained sequence-to-sequence language models have led to widespread success in many natural language generation tasks. However, there has been relatively less work on analyzing their ability to generate structured outputs such as…