We introduce the SaaS Algorithm for semi-supervised learning, which uses learning speed during stochastic gradient descent in a deep neural network to measure the quality of an iterative estimate of the posterior probability of unknown labels. Training speed in supervised learning correlates strongly with the percentage of correct labels, so we use it as an inference criterion for the unknown labels, without attempting to infer the model parameters at first. Despite its simplicity, SaaS achieves state-of-the-art results in semi-supervised learning benchmarks.

In this contribution, we present a novel approach for segmenting laser radar (lidar) imagery into geometric time-height cloud locations with a fully convolutional network (FCN). We describe a semi-supervised learning method to train the FCN by: pre-training the classification layers of the FCN with "weakly labeled" lidar data, using "unsupervised" pre-training with the cloud locations of the Wang & Sassen (2001) cloud mask algorithm, and fully supervised learning with hand-labeled cloud locations. We show the model achieves higher levels of cloud identification compared to the cloud mask algorithm.

Annotating temporal relations (TempRel) between events described in natural language is known to be labor intensive, partly because the total number of TempRels is quadratic in the number of events. As a result, only a small number of documents are typically annotated, limiting the coverage of various lexical/semantic phenomena. In order to improve existing approaches, one possibility is to make use of the readily available, partially annotated data (P as in partial) that cover more documents. However, missing annotations in P are known to hurt, rather than help, existing systems. This work is a case study in exploring various usages of P for TempRel extraction. Results show that despite missing annotations, P is still a useful supervision signal for this task within a constrained bootstrapping learning framework. The system described in this system is publicly available.

We propose a technique for declaratively specifying strategies for semi-supervised learning (SSL). The proposed method can be used to specify ensembles of semi-supervised learning, as well as agreement constraints and entropic regularization constraints between these learners, and can be used to model both well-known heuristics such as co-training and novel domain-specific heuristics. In addition to representing individual SSL heuristics, we show that multiple heuristics can also be automatically combined using Bayesian optimization methods. We show consistent improvements on a suite of well-studied SSL benchmarks, including a new state-of-the-art result on a difficult relation extraction task.

We build a virtual agent for learning language in a 2D maze-like world. The agent sees images of the surrounding environment, listens to a virtual teacher, and takes actions to receive rewards. It interactively learns the teacher's language from scratch based on two language use cases: sentence-directed navigation and question answering. It learns simultaneously the visual representations of the world, the language, and the action control. By disentangling language grounding from other computational routines and sharing a concept detection function between language grounding and prediction, the agent reliably interpolates and extrapolates to interpret sentences that contain new word combinations or new words missing from training sentences. The new words are transferred from the answers of language prediction. Such a language ability is trained and evaluated on a population of over 1.6 million distinct sentences consisting of 119 object words, 8 color words, 9 spatial-relation words, and 50 grammatical words. The proposed model significantly outperforms five comparison methods for interpreting zero-shot sentences. In addition, we demonstrate human-interpretable intermediate outputs of the model in the appendix.

Partial label learning (PLL) aims to solve the problem where each training instance is associated with a set of candidate labels, one of which is the correct label. Most PLL algorithms try to disambiguate the candidate label set, by either simply treating each candidate label equally or iteratively identifying the true label. Nonetheless, existing algorithms usually treat all labels and instances equally, and the complexities of both labels and instances are not taken into consideration during the learning stage. Inspired by the successful application of self-paced learning strategy in machine learning field, we integrate the self-paced regime into the partial label learning framework and propose a novel Self-Paced Partial-Label Learning (SP-PLL) algorithm, which could control the learning process to alleviate the problem by ranking the priorities of the training examples together with their candidate labels during each learning iteration. Extensive experiments and comparisons with other baseline methods demonstrate the effectiveness and robustness of the proposed method.

Despite the breakthroughs achieved by deep learning models in conventional supervised learning scenarios, their dependence on sufficient labeled training data in each class prevents effective applications of these deep models in situations where labeled training instances for a subset of novel classes are very sparse -- in the extreme case only one instance is available for each class. To tackle this natural and important challenge, one-shot learning, which aims to exploit a set of well labeled base classes to build classifiers for the new target classes that have only one observed instance per class, has recently received increasing attention from the research community. In this paper we propose a novel end-to-end deep triplet ranking network to perform one-shot learning. The proposed approach learns class universal image embeddings on the well labeled base classes under a triplet ranking loss, such that the instances from new classes can be categorized based on their similarity with the one-shot instances in the learned embedding space. Moreover, our approach can naturally incorporate the available one-shot instances from the new classes into the embedding learning process to improve the triplet ranking model. We conduct experiments on two popular datasets for one-shot learning. The results show the proposed approach achieves better performance than the state-of-the- art comparison methods.

Area under ROC (AUC) is an important metric for binary classification and bipartite ranking problems. However, it is difficult to directly optimizing AUC as a learning objective, so most existing algorithms are based on optimizing a surrogate loss to AUC. One significant drawback of these surrogate losses is that they require pairwise comparisons among training data, which leads to slow running time and increasing local storage for online learning. In this work, we describe a new surrogate loss based on a reformulation of the AUC risk, which does not require pairwise comparison but rankings of the predictions. We further show that the ranking operation can be avoided, and the learning objective obtained based on this surrogate enjoys linear complexity in time and storage. We perform experiments to demonstrate the effectiveness of the online and batch algorithms for AUC optimization based on the proposed surrogate loss.

With the advent of Big Data era, data reduction methods are highly demanded given its ability to simplify huge data, and ease complex learning processes. Concretely, algorithms that are able to filter relevant dimensions from a set of millions are of huge importance. Although effective, these techniques suffer from the "scalability" curse as well. In this work, we propose a distributed feature weighting algorithm, which is able to rank millions of features in parallel using large samples. This method, inspired by the well-known RELIEF algorithm, introduces a novel redundancy elimination measure that provides similar schemes to those based on entropy at a much lower cost. It also allows smooth scale up when more instances are demanded in feature estimations. Empirical tests performed on our method show its estimation ability in manifold huge sets --both in number of features and instances--, as well as its simplified runtime cost (specially, at the redundancy detection step).

We introduce KBGAN, an adversarial learning framework to improve the performances of a wide range of existing knowledge graph embedding models. Because knowledge graphs typically only contain positive facts, sampling useful negative training examples is a non-trivial task. Replacing the head or tail entity of a fact with a uniformly randomly selected entity is a conventional method for generating negative facts, but the majority of the generated negative facts can be easily discriminated from positive facts, and will contribute little towards the training. Inspired by generative adversarial networks (GANs), we use one knowledge graph embedding model as a negative sample generator to assist the training of our desired model, which acts as the discriminator in GANs. This framework is independent of the concrete form of generator and discriminator, and therefore can utilize a wide variety of knowledge graph embedding models as its building blocks. In experiments, we adversarially train two translation-based models, TransE and TransD, each with assistance from one of the two probability-based models, DistMult and ComplEx. We evaluate the performances of KBGAN on the link prediction task, using three knowledge base completion datasets: FB15k-237, WN18 and WN18RR. Experimental results show that adversarial training substantially improves the performances of target embedding models under various settings.