Recently, graph-based algorithms have drawn much attention because of their impressive success in semi-supervised setups. For better model performance, previous studies learn to transform the topology of the input graph. However, these works only focus on optimizing the original nodes and edges, leaving the direction of augmenting existing data unexplored. In this paper, by simulating the generation process of graph signals, we propose a novel heuristic pre-processing technique, namely ELectoral COllege (ELCO), which automatically expands new nodes and edges to refine the label similarity within a dense subgraph. Substantially enlarging the original training set with high-quality generated labeled data, our framework can effectively benefit downstream models. To justify the generality and practicality of ELCO, we couple it with the popular Graph Convolution Network and Graph Attention Network to perform extensive evaluations on three standard datasets. In all setups tested, our method boosts the average score of base models by a large margin of 4.7 points, as well as consistently outperforms the state-of-the-art. We release our code and data on https://github.com/RingBDStack/ELCO to guarantee reproducibility.

Self-supervised approaches such as Momentum Contrast (MoCo) can leverage unlabeled data to produce pretrained models for subsequent fine-tuning on labeled data. While MoCo has demonstrated promising results on natural image classification tasks, its application to medical imaging tasks like chest X-ray interpretation has been limited. Chest X-ray interpretation is fundamentally different from natural image classification in ways that may limit the applicability of self-supervised approaches. In this work, we investigate whether MoCo-pretraining leads to better representations or initializations for chest X-ray interpretation. We conduct MoCo-pretraining on CheXpert, a large labeled dataset of X-rays, followed by supervised fine-tuning experiments on the pleural effusion task. Using 0.1% of labeled training data, we find that a linear model trained on MoCo-pretrained representations outperforms one trained on representations without MoCo-pretraining by an AUC of 0.096 (95% CI 0.061, 0.130), indicating that MoCo-pretrained representations are of higher quality. Furthermore, a model fine-tuned end-to-end with MoCo-pretraining outperforms its non-MoCo-pretrained counterpart by an AUC of 0.037 (95% CI 0.015, 0.062) with the 0.1% label fraction. These AUC improvements are observed for all label fractions for both the linear model and an end-to-end fine-tuned model with the greater improvements for smaller label fractions. Finally, we observe similar results on a small, target chest X-ray dataset (Shenzhen dataset for tuberculosis) with MoCo-pretraining done on the source dataset (CheXpert), which suggests that pretraining on unlabeled X-rays can provide transfer learning benefits for a target task. Our study demonstrates that MoCo-pretraining provides high-quality representations and transferable initializations for chest X-ray interpretation.

In Natural Language Processing (NLP), pretrained language models (LMs) that are transferred to downstream tasks have been recently shown to achieve state-of-the-art results. However, standard fine-tuning can degrade the general-domain representations captured during pretraining. To address this issue, we introduce a new regularization technique, AFTER; domain Adversarial Fine-Tuning as an Effective Regularizer. Specifically, we complement the task-specific loss used during fine-tuning with an adversarial objective. This additional loss term is related to an adversarial classifier, that aims to discriminate between in-domain and out-of-domain text representations. In-domain refers to the labeled dataset of the task at hand while out-of-domain refers to unlabeled data from a different domain. Intuitively, the adversarial classifier acts as a regularizer which prevents the model from overfitting to the task-specific domain. Empirical results on various natural language understanding tasks show that AFTER leads to improved performance compared to standard fine-tuning.

The elastic-net is among the most widely used types of regularization algorithms, commonly associated with the problem of supervised generalized linear model estimation via penalized maximum likelihood. Its nice properties originate from a combination of $\ell_1$ and $\ell_2$ norms, which endow this method with the ability to select variables taking into account the correlations between them. In the last few years, semi-supervised approaches, that use both labeled and unlabeled data, have become an important component in the statistical research. Despite this interest, however, few researches have investigated semi-supervised elastic-net extensions. This paper introduces a novel solution for semi-supervised learning of sparse features in the context of generalized linear model estimation: the generalized semi-supervised elastic-net (s2net), which extends the supervised elastic-net method, with a general mathematical formulation that covers, but is not limited to, both regression and classification problems. We develop a flexible and fast implementation for s2net in R, and its advantages are illustrated using both real and synthetic data sets.

Many people are aware of AI or Artificial Intelligence and its meaning, especially in the way that it is often portrayed through movies. These movies are often exciting and captivate our imaginations. Machine learning, while similar to AI, is defined differently. A way to explain this in layman's terms is that AI is the breadth of knowledge contained and used by a system, while machine learning is the algorithms or processes in which the system gains the knowledge and assimilates it for future use. In human terms, AI would be all the information and knowledge you already have, while machine learning would be likened unto the steps you choose to acquire that knowledge, such as reading, observing, studying, or even making mistakes.

In machine learning, one must acquire labels to help supervise a model that will be able to generalize to unseen data. However, the labeling process can be tedious, long, costly, and error-prone. It is often the case that most of our data is unlabeled. Semi-supervised learning (SSL) alleviates that by making strong assumptions about the relation between the labels and the input data distribution. This paradigm has been successful in practice, but most SSL algorithms end up fully trusting the few available labels. In real life, both humans and automated systems are prone to mistakes; it is essential that our algorithms are able to work with labels that are both few and also unreliable. Our work aims to perform an extensive empirical evaluation of existing graph-based semi-supervised algorithms, like Gaussian Fields and Harmonic Functions, Local and Global Consistency, Laplacian Eigenmaps, Graph Transduction Through Alternating Minimization. To do that, we compare the accuracy of classifiers while varying the amount of labeled data and label noise for many different samples. Our results show that, if the dataset is consistent with SSL assumptions, we are able to detect the noisiest instances, although this gets harder when the number of available labels decreases. Also, the Laplacian Eigenmaps algorithm performed better than label propagation when the data came from high-dimensional clusters.

We develop an algorithm for adapting a semantic segmentation model that is trained using a labeled source domain to generalize well in an unlabeled target domain. A similar problem has been studied extensively in the unsupervised domain adaptation (UDA) literature, but existing UDA algorithms require access to both the source domain labeled data and the target domain unlabeled data for training a domain agnostic semantic segmentation model. Relaxing this constraint enables a user to adapt pretrained models to generalize in a target domain, without requiring access to source data. To this end, we learn a prototypical distribution for the source domain in an intermediate embedding space. This distribution encodes the abstract knowledge that is learned from the source domain. We then use this distribution for aligning the target domain distribution with the source domain distribution in the embedding space. We provide theoretical analysis and explain conditions under which our algorithm is effective. Experiments on benchmark adaptation task demonstrate our method achieves competitive performance even compared with joint UDA approaches.

Real-world data often exhibits long-tailed distributions with heavy class imbalance, posing great challenges for deep recognition models. We identify a persisting dilemma on the value of labels in the context of imbalanced learning: on the one hand, supervision from labels typically leads to better results than its unsupervised counterparts; on the other hand, heavily imbalanced data naturally incurs "label bias" in the classifier, where the decision boundary can be drastically altered by the majority classes. In this work, we systematically investigate these two facets of labels. We demonstrate, theoretically and empirically, that class-imbalanced learning can significantly benefit in both semi-supervised and self-supervised manners. Specifically, we confirm that (1) positively, imbalanced labels are valuable: given more unlabeled data, the original labels can be leveraged with the extra data to reduce label bias in a semi-supervised manner, which greatly improves the final classifier; (2) negatively however, we argue that imbalanced labels are not useful always: classifiers that are first pre-trained in a self-supervised manner consistently outperform their corresponding baselines. Extensive experiments on large-scale imbalanced datasets verify our theoretically grounded strategies, showing superior performance over previous state-of-the-arts. Our intriguing findings highlight the need to rethink the usage of imbalanced labels in realistic long-tailed tasks. Code is available at https://github.com/YyzHarry/imbalanced-semi-self.

Current deep domain adaptation methods used in computer vision have mainly focused on learning discriminative and domain-invariant features across different domains. In this paper, we present a novel "deep adversarial transition learning" (DATL) framework that bridges the domain gap by projecting the source and target domains into intermediate, transitional spaces through the employment of adjustable, cross-grafted generative network stacks and effective adversarial learning between transitions. Specifically, we construct variational auto-encoders (VAE) for the two domains, and form bidirectional transitions by cross-grafting the VAEs' decoder stacks. Furthermore, generative adversarial networks (GAN) are employed for domain adaptation, mapping the target domain data to the known label space of the source domain. The overall adaptation process hence consists of three phases: feature representation learning by VAEs, transitions generation, and transitions alignment by GANs. Experimental results demonstrate that our method outperforms the state-of-the art on a number of unsupervised domain adaptation benchmarks.

A growing specter in the rise of machine learning is whether the decisions made by machine learning models are fair. While research is already underway to formalize a machine-learning concept of fairness and to design frameworks for building fair models with sacrifice in accuracy, most are geared toward either supervised or unsupervised learning. Yet two observations inspired us to wonder whether semi-supervised learning might be useful to solve discrimination problems. First, previous study showed that increasing the size of the training set may lead to a better trade-off between fairness and accuracy. Second, the most powerful models today require an enormous of data to train which, in practical terms, is likely possible from a combination of labeled and unlabeled data. Hence, in this paper, we present a framework of fair semi-supervised learning in the pre-processing phase, including pseudo labeling to predict labels for unlabeled data, a re-sampling method to obtain multiple fair datasets and lastly, ensemble learning to improve accuracy and decrease discrimination. A theoretical decomposition analysis of bias, variance and noise highlights the different sources of discrimination and the impact they have on fairness in semi-supervised learning. A set of experiments on real-world and synthetic datasets show that our method is able to use unlabeled data to achieve a better trade-off between accuracy and discrimination.