相关论文: Node Classification on Graphs with Few-Shot Novel …

Node representations, or embeddings, are low-dimensional vectors that capture node properties, typically learned through unsupervised structural similarity objectives or supervised tasks. While recent efforts have focused on explaining…

Few-shot named entity recognition (NER) enables us to build a NER system for a new domain using very few labeled examples. However, existing prototypical networks for this task suffer from roughly estimated label dependency and closely…

Node features bolster graph-based learning when exploited jointly with network structure. However, a lack of nodal attributes is prevalent in graph data. We present a framework to recover completely missing node features for a set of…

Word embedding, which refers to low-dimensional dense vector representations of natural words, has demonstrated its power in many natural language processing tasks. However, it may suffer from the inaccurate and incomplete information…

We study the problem of building text classifiers with little or no training data, commonly known as zero and few-shot text classification. In recent years, an approach based on neural textual entailment models has been found to give strong…

The recent success of graph neural networks has significantly boosted molecular property prediction, advancing activities such as drug discovery. The existing deep neural network methods usually require large training dataset for each…

Learning novel classes from a very few labeled samples has attracted increasing attention in machine learning areas. Recent research on either meta-learning based or transfer-learning based paradigm demonstrates that gaining information on…

When dealing with large graphs, such as those that arise in the context of online social networks, a subset of nodes may be labeled. These labels can indicate demographic values, interest, beliefs or other characteristics of the nodes…

Graph Neural Networks (GNNs) have become popular in Graph Representation Learning (GRL). One fundamental application is few-shot node classification. Most existing methods follow the meta learning paradigm, showing the ability of fast…

Graph neural networks (GNNs) achieve strong performance on homophilic graphs but often struggle under heterophily, where adjacent nodes frequently belong to different classes. We propose an interpretable and adaptive framework for…

Most real-world datasets are inherently heterogeneous graphs, which involve a diversity of node and relation types. Heterogeneous graph embedding is to learn the structure and semantic information from the graph, and then embed it into the…

The real-world networks often compose of different types of nodes and edges with rich semantics, widely known as heterogeneous information network (HIN). Heterogeneous network embedding aims to embed nodes into low-dimensional vectors which…

Graph Neural Networks (GNNs) require a relatively large number of labeled nodes and a reliable/uncorrupted graph connectivity structure in order to obtain good performance on the semi-supervised node classification task. The performance of…

Graph neural networks have been demonstrated as a powerful paradigm for effectively learning graph-structured data on the web and mining content from it.Current leading graph models require a large number of labeled samples for training,…

The task of node classification is to infer unknown node labels, given the labels for some of the nodes along with the network structure and other node attributes. Typically, approaches for this task assume homophily, whereby neighboring…

The challenges of training and inference in few-shot environments persist in the area of graph representation learning. The quality and quantity of labels are often insufficient due to the extensive expert knowledge required to annotate…

The focus of recent meta-learning research has been on the development of learning algorithms that can quickly adapt to test time tasks with limited data and low computational cost. Few-shot learning is widely used as one of the standard…

The progress in hyperbolic neural networks (HNNs) research is hindered by their absence of inductive bias mechanisms, which are essential for generalizing to new tasks and facilitating scalable learning over large datasets. In this paper,…

We study the problem of few shot learning for named entity recognition. Specifically, we leverage the semantic information in the names of the labels as a way of giving the model additional signal and enriched priors. We propose a neural…

Few/Zero-shot learning is a big challenge of many classifications tasks, where a classifier is required to recognise instances of classes that have very few or even no training samples. It becomes more difficult in multi-label…