Related papers: Consistency of semi-supervised learning algorithms…

Two approaches for graph based semi-supervised learning are proposed. The firstapproach is based on iteration of an affine map. A key element of the affine map iteration is sparsematrix-vector multiplication, which has several very…

Graphs have become increasingly popular in modeling structures and interactions in a wide variety of problems during the last decade. Graph-based clustering and semi-supervised classification techniques have shown impressive performance.…

Self-supervised learning, which learns by constructing artificial labels given only the input signals, has recently gained considerable attention for learning representations with unlabeled datasets, i.e., learning without any…

We consider the problem of classifying a medical image dataset when we have a limited amounts of labels. This is very common yet challenging setting as labelled data is expensive, time consuming to collect and may require expert knowledge.…

For semi-supervised techniques to be applied safely in practice we at least want methods to outperform their supervised counterparts. We study this question for classification using the well-known quadratic surrogate loss function. Using a…

Node classification on graphs is a significant task with a wide range of applications, including social analysis and anomaly detection. Even though graph neural networks (GNNs) have produced promising results on this task, current…

Speaker identification in the household scenario (e.g., for smart speakers) is typically based on only a few enrollment utterances but a much larger set of unlabeled data, suggesting semisupervised learning to improve speaker profiles. We…

Graph-based semi-supervised node classification (GraphSSC) has wide applications, ranging from networking and security to data mining and machine learning, etc. However, existing centralized GraphSSC methods are impractical to solve many…

The emergent reasoning capabilities of Large Language Models (LLMs) offer a transformative paradigm for analyzing text-attributed graphs. While instruction tuning is the prevailing method for adapting pre-trained LLMs to graph learning…

Effective convolutional neural networks are trained on large sets of labeled data. However, creating large labeled datasets is a very costly and time-consuming task. Semi-supervised learning uses unlabeled data to train a model with higher…

To address semi-supervised learning from both labeled and unlabeled data, we present a novel meta-learning scheme. We particularly consider that labeled and unlabeled data share disjoint ground truth label sets, which can be seen tasks like…

The success of graph neural networks on graph-based web mining highly relies on abundant human-annotated data, which is laborious to obtain in practice. When only few labeled nodes are available, how to improve their robustness is a key to…

Supervised machine learning frameworks rely on extensive labeled datasets for robust performance on real-world tasks. However, there is a lack of large annotated datasets in audio and music domains, as annotating such recordings is…

Learning algorithms normally assume that there is at most one annotation or label per data point. However, in some scenarios, such as medical diagnosis and on-line collaboration,multiple annotations may be available. In either case,…

In this work, we address semi-supervised classification of graph data, where the categories of those unlabeled nodes are inferred from labeled nodes as well as graph structures. Recent works often solve this problem via advanced graph…

Due to the cost of labeling nodes, classifying a node in a sparsely labeled graph while maintaining the prediction accuracy deserves attention. The key point is how the algorithm learns sufficient information from more neighbors with…

We study distributed optimization of finite-degree polynomial Laplacian spectral objectives under fixed topology and a global weight budget, targeting the collective behavior of the entire spectrum rather than a few extremal eigenvalues. By…

Deep networks are successfully used as classification models yielding state-of-the-art results when trained on a large number of labeled samples. These models, however, are usually much less suited for semi-supervised problems because of…

Neural abstractive summarization methods often require large quantities of labeled training data. However, labeling large amounts of summarization data is often prohibitive due to time, financial, and expertise constraints, which has…

Continual learning (CL) has shown promising results and comparable performance to learning at once in a fully supervised manner. However, CL strategies typically require a large number of labeled samples, making their real-life deployment…