Search for: All records

A quantification learning task estimates class ratios or class distribution given a test set. Quantification learning is useful for a variety of application domains such as commerce, public health, and politics. For instance, it is desirable to automatically estimate the proportion of customer satisfaction in different aspects from product reviews to improve customer relationships. We formulate the quantification learning problem as a maximum likelihood problem and propose the first end-to-end Deep Quantification Network (DQN) framework. DQN jointly learns quantification feature representations and directly predicts the class distribution. Compared to classification-based quantification methods, DQN avoids three separate steps: classification of individual instances, calculation of the predicted class ratios, and class ratio adjustment to account for classification errors. We evaluated DQN on four public datasets, ranging from movie and product reviews to multi-class news. We compared DQN against six existing quantification methods and conducted a sensitivity analysis of DQN performance. Compared to the best existing method in our study, (1) DQN reduces Mean Absolute Error (MAE) by about 35%. (2) DQN uses around 40% less training samples to achieve a comparable MAE. 

Adversarial examples are carefully constructed modifications to an input that completely change the output of a classifier but are imperceptible to humans. Despite these successful attacks for continuous data (such as image and audio samples), generating adversarial examples for discrete structures such as text has proven significantly more challenging. In this paper we formulate the attacks with discrete input on a set function as an optimization task. We prove that this set function is submodular for some popular neural network text classifiers under simplifying assumption. This finding guarantees a 1−1/e approximation factor for attacks that use the greedy algorithm. Meanwhile, we show how to use the gradient of the attacked classifier to guide the greedy search. Empirical studies with our proposed optimization scheme show significantly improved attack ability and efficiency, on three different text classification tasks over various baselines. We also use a joint sentence and word paraphrasing technique to maintain the original semantics and syntax of the text. This is validated by a human subject evaluation in subjective metrics on the quality and semantic coherence of our generated adversarial text. 

Maximum Inner Product Search (MIPS) is an important task in many machine learning applications such as the prediction phase of low-rank matrix factorization models and deep learning models. Recently, there has been substantial research on how to perform MIPS in sub-linear time, but most of the existing work does not have the flexibility to control the trade-off between search efficiency and search quality. In this paper, we study the important problem of MIPS with a computational budget. By carefully studying the problem structure of MIPS, we develop a novel Greedy-MIPS algorithm, which can handle budgeted MIPS by design. While simple and intuitive, Greedy-MIPS yields surprisingly superior performance compared to state-of-the-art approaches. As a specific example, on a candidate set containing half a million vectors of dimension 200, Greedy-MIPS runs 200x faster than the naive approach while yielding search results with the top-5 precision greater than 75%. 

Bio/artificial hybrid nanosystems based on biological matter and synthetic nanoparticles (NPs) remain a holy grail of materials science. Herein, inspired by the well‐defined metal–organic framework (MOF) with diverse chemical diversities, the concept of “armored red blood cells” (armored RBCs) is introduced, which are native RBCs assembled within and protected by a functional exoskeleton of interlinked MOF NPs. Exoskeletons are generated within seconds through MOF NP interlocking based on metal‐phenolic coordination and RBC membrane/NP complexation via hydrogen‐bonding interactions at the cellular interface. Armored RBC formation is shown to be generalizable to many classes of MOF NPs or any NPs that can be coated by MOF. Moreover, it is found that armored RBCs preserve the original properties of RBCs (such as oxygen carrier capability and good ex ovo/in vivo circulation property) and show enhanced resistance against external stressors (like osmotic pressure, detergent, toxic NPs, and freezing conditions). By modifying the physicochemical properties of MOF NPs, armored RBCs provide the capability for blood nitric oxide sensing or multimodal imaging. The synthesis of armored RBCs is straightforward, reliable, and reversible and hence, represent a new class of hybrid biomaterials with a broad range of functionalities.