Eliciting labels from crowds is a potential way to obtain large labeled data. Despite a variety of methods developed for learning from crowds, a key challenge remains unsolved: learning from crowds without knowing the information structure among the crowds a priori, when some people of the crowds make highly correlated mistakes and some of them label effortlessly (e.g. randomly). We propose an information theoretic approach, Max-MIG, for joint learning from crowds, with a common assumption: the crowdsourced labels and the data are independent conditioning on the ground truth. Max-MIG simultaneously aggregates the crowdsourced labels and learns an accurate data classifier. Furthermore, we devise an accurate data-crowds forecaster that employs both the data and the crowdsourced labels to forecast the ground truth. To the best of our knowledge, this is the first algorithm that solves the aforementioned challenge of learning from crowds. In addition to the theoretical validation, we also empirically show that our algorithm achieves the new state-of-the-art results in most settings, including the real-world data, and is the first algorithm that is robust to various information structures. Codes are available at https://github.com/Newbeeer/Max-MIG

Fusing data from multiple modalities provides more information to train machine learning systems. However, it is prohibitively expensive and timeconsuming to label each modality with a large amount of data, which leads to a crucial problem of semi-supervised multi-modal learning. Existing methods suffer from either ineffective fusion across modalities or lack of theoretical guarantees under proper assumptions. In this paper, we propose a novel information-theoretic approach -namely, Total Correlation Gain Maximization (TCGM) -for semisupervised multi-modal learning, which is endowed with promising properties: (i) it can utilize effectively the information across different modalities of unlabeled data points to facilitate training classifiers of each modality (ii) it has theoretical guarantee to identify Bayesian classifiers, i.e., the ground truth posteriors of all modalities. Specifically, by maximizing TC-induced loss (namely TC gain) over classifiers of all modalities, these classifiers can cooperatively discover the equivalent class of ground-truth classifiers; and identify the unique ones by leveraging limited percentage of labeled data. We apply our method to various tasks and achieve state-of-the-art results, including the news classification (Newsgroup dataset), emotion recognition (IEMOCAP and MOSI datasets), and disease prediction (Alzheimer's Disease Neuroimaging Initiative dataset).

No abstract

Ensuring generalization to unseen environments remains a challenge. Domain shift can lead to substantially degraded performance unless shifts are wellexercised within the available training environments. We introduce a simple robust estimation criterion -transfer risk -that is specifically geared towards optimizing transfer to new environments. Effectively, the criterion amounts to finding a representation that minimizes the risk of applying any optimal predictor trained on one environment to another. The transfer risk essentially decomposes into two terms, a direct transfer term and a weighted gradientmatching term arising from the optimality of per-environment predictors. Although inspired by IRM, we show that transfer risk serves as a better outof-distribution generalization criterion, both theoretically and empirically. We further demonstrate the impact of optimizing such transfer risk on two controlled settings, each representing a different pattern of environment shift, as well as on two real-world datasets. Experimentally, the approach outperforms baselines across various out-of-distribution generalization tasks.Code is available at https://github.com/Newbeeer/TRM.