Real-world data often contains intrinsic ambiguity that the common single-hard-label annotation paradigm ignores. Standard training using ambiguous data with these hard labels may produce overly confident models and thus leading to poor generalization. In this paper, we propose a novel framework called Quantized Label Learning (QLL) to alleviate this issue. First, we formulate QLL as learning from (very) ambiguous data with hard labels: ideally, each ambiguous instance should be associated with a ground-truth soft-label distribution describing its corresponding probabilistic weight in each class, however, this is usually not accessible; in practice, we can only observe a quantized label, i.e., a hard label sampled (quantized) from the corresponding ground-truth soft-label distribution, of each instance, which can be seen as a biased approximation of the ground-truth soft-label. Second, we propose a Class-wise Positive-Unlabeled (CPU) risk estimator that allows us to train accurate classifiers from only ambiguous data with quantized labels. Third, to simulate ambiguous datasets with quantized labels in the real world, we design a mixing-based ambiguous data generation procedure for empirical evaluation. Experiments demonstrate that our CPU method can significantly improve model generalization performance and outperform the baselines.

Distribution shift (DS) may have two levels: the distribution itself changes, and the support (i.e., the set where the probability density is non-zero) also changes. When considering the support change between the training and test distributions, there can be four cases: (i) they exactly match; (ii) the training support is wider (and thus covers the test support); (iii) the test support is wider; (iv) they partially overlap. Existing methods are good at cases (i) and (ii), while cases (iii) and (iv) are more common nowadays but still under-explored. In this paper, we generalize importance weighting (IW), a golden solver for cases (i) and (ii), to a universal solver for all cases. Specifically, we first investigate why IW might fail in cases (iii) and (iv); based on the findings, we propose generalized IW (GIW) that could handle cases (iii) and (iv) and would reduce to IW in cases (i) and (ii). In GIW, the test support is split into an in-training (IT) part and an out-of-training (OOT) part, and the expected risk is decomposed into a weighted classification term over the IT part and a standard classification term over the OOT part, which guarantees the risk consistency of GIW. Then, the implementation of GIW consists of three components: (a) the split of validation data is carried out by the one-class support vector machine, (b) the first term of the empirical risk can be handled by any IW algorithm given training data and IT validation data, and (c) the second term just involves OOT validation data. Experiments demonstrate that GIW is a universal solver for DS problems, outperforming IW methods in cases (iii) and (iv).

Corruption is frequently observed in collected data and has been extensively studied in machine learning under different corruption models. Despite this, there remains a limited understanding of how these models relate such that a unified view of corruptions and their consequences on learning is still lacking. In this work, we formally analyze corruption models at the distribution level through a general, exhaustive framework based on Markov kernels. We highlight the existence of intricate joint and dependent corruptions on both labels and attributes, which are rarely touched by existing research. Further, we show how these corruptions affect standard supervised learning by analyzing the resulting changes in Bayes Risk. Our findings offer qualitative insights into the consequences of "more complex" corruptions on the learning problem, and provide a foundation for future quantitative comparisons. Applications of the framework include corruption-corrected learning, a subcase of which we study in this paper by theoretically analyzing loss correction with respect to different corruption instances.

A key assumption in supervised learning is that training and test data follow the same probability distribution. However, this fundamental assumption is not always satisfied in practice, e.g., due to changing environments, sample selection bias, privacy concerns, or high labeling costs. Transfer learning (TL) relaxes this assumption and allows us to learn under distribution shift. Classical TL methods typically rely on importance-weighting -- a predictor is trained based on the training losses weighted according to the importance (i.e., the test-over-training density ratio). However, as real-world machine learning tasks are becoming increasingly complex, high-dimensional, and dynamical, novel approaches are explored to cope with such challenges recently. In this article, after introducing the foundation of TL based on importance-weighting, we review recent advances based on joint and dynamic importance-predictor estimation. Furthermore, we introduce a method of causal mechanism transfer that incorporates causal structure in TL. Finally, we discuss future perspectives of TL research.

To cope with high annotation costs, training a classifier only from weakly supervised data has attracted a great deal of attention these days. Among various approaches, strengthening supervision from completely unsupervised classification is a promising direction, which typically employs class priors as the only supervision and trains a binary classifier from unlabeled (U) datasets. While existing risk-consistent methods are theoretically grounded with high flexibility, they can learn only from two U sets. In this paper, we propose a new approach for binary classification from m U-sets for $m\ge2$. Our key idea is to consider an auxiliary classification task called surrogate set classification (SSC), which is aimed at predicting from which U set each observed data is drawn. SSC can be solved by a standard (multi-class) classification method, and we use the SSC solution to obtain the final binary classifier through a certain linear-fractional transformation. We built our method in a flexible and efficient end-to-end deep learning framework and prove it to be classifier-consistent. Through experiments, we demonstrate the superiority of our proposed method over state-of-the-art methods.

Under distribution shift (DS) where the training data distribution differs from the test one, a powerful technique is importance weighting (IW) which handles DS in two separate steps: weight estimation (WE) estimates the test-over-training density ratio and weighted classification (WC) trains the classifier from weighted training data. However, IW cannot work well on complex data, since WE is incompatible with deep learning. In this paper, we rethink IW and theoretically show it suffers from a circular dependency: we need not only WE for WC, but also WC for WE where a trained deep classifier is used as the feature extractor (FE). To cut off the dependency, we try to pretrain FE from unweighted training data, which leads to biased FE. To overcome the bias, we propose an end-to-end solution dynamic IW that iterates between WE and WC and combines them in a seamless manner, and hence our WE can also enjoy deep networks and stochastic optimizers indirectly. Experiments with two representative types of DS on three popular datasets show that our dynamic IW compares favorably with state-of-the-art methods.

Ordinary (pointwise) binary classification aims to learn a binary classifier from pointwise labeled data. However, such pointwise labels may not be directly accessible due to privacy, confidentiality, or security considerations. In this case, can we still learn an accurate binary classifier? This paper proposes a novel setting, namely pairwise comparison (Pcomp) classification, where we are given only pairs of unlabeled data that we know one is more likely to be positive than the other, instead of pointwise labeled data. Pcomp classification is useful for private or subjective classification tasks. To solve this problem, we present a mathematical formulation for the generation process of pairwise comparison data, based on which we exploit an unbiased risk estimator (URE) to train a binary classifier by empirical risk minimization and establish an estimation error bound. We first prove that a URE can be derived and improve it using correction functions. Then, we start from the noisy-label learning perspective to introduce a progressive URE and improve it by imposing consistency regularization. Finally, experiments validate the effectiveness of our proposed solutions for Pcomp classification.

A default assumption in many machine learning scenarios is that the training and test samples are drawn from the same probability distribution. However, such an assumption is often violated in the real world due to non-stationarity of the environment or bias in sample selection. In this work, we consider a prevalent setting called covariate shift, where the input distribution differs between the training and test stages while the conditional distribution of the output given the input remains unchanged. Most of the existing methods for covariate shift adaptation are two-step approaches, which first calculate the importance weights and then conduct importance-weighted empirical risk minimization. In this paper, we propose a novel one-step approach that jointly learns the predictive model and the associated weights in one optimization by minimizing an upper bound of the test risk. We theoretically analyze the proposed method and provide a generalization error bound. We also empirically demonstrate the effectiveness of the proposed method.

From two unlabeled (U) datasets with different class priors, we can train a binary classifier by empirical risk minimization, which is called UU classification. It is promising since UU methods are compatible with any neural network (NN) architecture and optimizer as if it is standard supervised classification. In this paper, however, we find that UU methods may suffer severe overfitting, and there is a high co-occurrence between the overfitting and the negative empirical risk regardless of datasets, NN architectures, and optimizers. Hence, to mitigate the overfitting problem of UU methods, we propose to keep two parts of the empirical risk (i.e., false positive and false negative) non-negative by wrapping them in a family of correction functions. We theoretically show that the corrected risk estimator is still asymptotically unbiased and consistent; furthermore we establish an estimation error bound for the corrected risk minimizer. Experiments with feedforward/residual NNs on standard benchmarks demonstrate that our proposed correction can successfully mitigate the overfitting of UU methods and significantly improve the classification accuracy.

Empirical risk minimization (ERM), with proper loss function and regularization, is the common practice of supervised classification. In this paper, we study training arbitrary (from linear to deep) binary classifier from only unlabeled (U) data by ERM but not by clustering in the geometric space. A two-step ERM is considered: first an unbiased risk estimator is designed, and then the empirical training risk is minimized. This approach is advantageous in that we can also evaluate the empirical validation risk, which is indispensable for hyperparameter tuning when some validation data is split from U training data instead of labeled test data. We prove that designing such an estimator is impossible given a single set of U data, but it becomes possible given two sets of U data with different class priors. This answers a fundamental question in weakly-supervised learning, namely what the minimal supervision is for training any binary classifier from only U data. Since the proposed learning method is based on unbiased risk estimates, the asymptotic consistency of the learned classifier is certainly guaranteed. Experiments demonstrate that the proposed method could successfully train deep models like ResNet and outperform state-of-the-art methods for learning from two sets of U data.