Many statistical learning models hold an assumption that the training data and the future unlabeled data are drawn from the same distribution. However, this assumption is difficult to fulfill in real-world scenarios and creates barriers in reusing existing labels from similar application domains. Transfer Learning is intended to relax this assumption by modeling relationships between domains, and is often applied in deep learning applications to reduce the demand for labeled data and training time. Despite recent advances in exploring deep learning models with visual analytics tools, little work has explored the issue of explaining and diagnosing the knowledge transfer process between deep learning models. In this paper, we present a visual analytics framework for the multi-level exploration of the transfer learning processes when training deep neural networks. Our framework establishes a multi-aspect design to explain how the learned knowledge from the existing model is transferred into the new learning task when training deep neural networks. Based on a comprehensive requirement and task analysis, we employ descriptive visualization with performance measures and detailed inspections of model behaviors from the statistical, instance, feature, and model structure levels. We demonstrate our framework through two case studies on image classification by fine-tuning AlexNets to illustrate how analysts can utilize our framework.

Deep neural networks (DNN) have shown great success in many computer vision applications. However, they are also known to be susceptible to backdoor attacks. When conducting backdoor attacks, most of the existing approaches assume that the targeted DNN is always available, and an attacker can always inject a specific pattern to the training data to further fine-tune the DNN model. However, in practice, such attack may not be feasible as the DNN model is encrypted and only available to the secure enclave. In this paper, we propose a novel black-box backdoor attack technique on face recognition systems, which can be conducted without the knowledge of the targeted DNN model. To be specific, we propose a backdoor attack with a novel color stripe pattern trigger, which can be generated by modulating LED in a specialized waveform. We also use an evolutionary computing strategy to optimize the waveform for backdoor attack. Our backdoor attack can be conducted in a very mild condition: 1) the adversary cannot manipulate the input in an unnatural way (e.g., injecting adversarial noise); 2) the adversary cannot access the training database; 3) the adversary has no knowledge of the training model as well as the training set used by the victim party. We show that the backdoor trigger can be quite effective, where the attack success rate can be up to $88\%$ based on our simulation study and up to $40\%$ based on our physical-domain study by considering the task of face recognition and verification based on at most three-time attempts during authentication. Finally, we evaluate several state-of-the-art potential defenses towards backdoor attacks, and find that our attack can still be effective. We highlight that our study revealed a new physical backdoor attack, which calls for the attention of the security issue of the existing face recognition/verification techniques.

While deep neural networks achieve great performance on fitting the training distribution, the learned networks are prone to overfitting and are susceptible to adversarial attacks. In this regard, a number of mixup based augmentation methods have been recently proposed. However, these approaches mainly focus on creating previously unseen virtual examples and can sometimes provide misleading supervisory signal to the network. To this end, we propose Puzzle Mix, a mixup method for explicitly utilizing the saliency information and the underlying statistics of the natural examples. This leads to an interesting optimization problem alternating between the multi-label objective for optimal mixing mask and saliency discounted optimal transport objective. Our experiments show Puzzle Mix achieves the state of the art generalization and the adversarial robustness results compared to other mixup methods on CIFAR-100, Tiny-ImageNet, and ImageNet datasets. The source code is available at https://github.com/snu-mllab/PuzzleMix.

This paper takes a first step towards a critical thinking curriculum for neural auto-regressive language models. We introduce a synthetic text corpus of deductively valid arguments, and use this artificial argument corpus to train and evaluate GPT-2. Significant transfer learning effects can be observed: Training a model on a few simple core schemes allows it to accurately complete conclusions of different, and more complex types of arguments, too. The language models seem to connect and generalize the core argument schemes in a correct way. Moreover, we obtain consistent and promising results for the GLUE and SNLI benchmarks. The findings suggest that there might exist a representative sample of paradigmatic instances of good reasoning that will suffice to acquire general reasoning skills and that might form the core of a critical thinking curriculum for language models.

According to GHO (Global Health Observatory (GHO), the high prevalence of a large variety of diseases such as Ischaemic heart disease, stroke, lung cancer disease and lower respiratory infections have remained the top killers during the past decade. The growth in the number of mortalities caused by these disease is due to the very delayed symptoms'detection. Since in the early stages, the symptoms are insignificant and similar to those of benign diseases (e.g. the flu ), and we can only detect the disease at an advanced stage. In addition, The high frequency of improper practices that are harmful to health, the hereditary factors, and the stressful living conditions can increase the death rates. Many researches dealt with these fatal disease, and most of them applied advantage machine learning models to deal with image diagnosis. However the drawback is that imagery permit only to detect disease at a very delayed stage and then patient can hardly be saved. In this Paper we present our new approach "DeepLCP" to predict fatal diseases that threaten people's lives. It's mainly based on raw and heterogeneous data of the concerned (or under-tested) person. "DeepLCP" results of a combination combination of the Natural Language Processing (NLP) and the deep learning paradigm.The experimental results of the proposed model in the case of Lung cancer prediction have approved high accuracy and a low loss data rate during the validation of the disease prediction.

Indeed, previous works demonstrated how combined models of this type can speedup learning and/or achieve better performance also in continuous problems domains. In particular, the research reported in (Riedmiller & VoigtHinder, 2012; Mattner, Lange & Riedmiller, 2012; Ha & Schmidhuber, 2018) demonstrated how the addition of feature-9 extraction network is beneficial, at least in the case of problems that can benefit from dimensionality reduction and that involve a perspective transformation of the observation states. In this paper we report new data that provide further evidences on the utility of feature extractions, permit to compare the relative efficacy of alternative methods, and demonstrate the importance of updating the feature extracted during the training of the policy network. The data reported further support the hypothesis that feature extraction can enhance learning, also in the case of continuous problem domains in which relevant features extend over space and time. Indeed, the usage of feature extraction enabled us to obtain significantly better results in 3 of the 4 problems considered. The utilization of problems that involve agents operating on the basis of egocentric information, instead of allocentric information as in previous studies, demonstrates that feature extraction can be advantageous in general terms, irrespectively from the necessity to perform a perspective transformation. Moreover, the utilization of problems that involve relatively compact observation vectors, instead than large observation vectors as in previous studies, demonstrates that feature extraction can be advantageous also in problems that do not benefit from dimensionality reduction. The data collected by training the feature extracting network before the policy network, as in previous studies, or also during the training of the policy network demonstrates that the latter technique is much more effective and that the method proposed in this paper for realizing the continuous training is sound. Finally, the comparison of different self-supervised techniques for extracting useful features demonstrates that sequence-to-sequence learning produces the best results and outperform the other methods used in previous studies in the problem considered.

Extracting event temporal relations is a critical task for information extraction and plays an important role in natural language understanding. Prior systems leverage deep learning and pre-trained language models to improve the performance of the task. However, these systems often suffer from two short-comings: 1) when performing maximum a posteriori (MAP) inference based on neural models, previous systems only used structured knowledge that are assumed to be absolutely correct, i.e., hard constraints; 2) biased predictions on dominant temporal relations when training with a limited amount of data. To address these issues, we propose a framework that enhances deep neural network with distributional constraints constructed by probabilistic domain knowledge. We solve the constrained inference problem via Lagrangian Relaxation and apply it on end-to-end event temporal relation extraction tasks. Experimental results show our framework is able to improve the baseline neural network models with strong statistical significance on two widely used datasets in news and clinical domains.

We consider the problem of evaluating representations of data for use in solving a downstream task. We propose to measure the quality of a representation by the complexity of learning a predictor on top of the representation that achieves low loss on a task of interest, and introduce two methods, surplus description length (SDL) and $\varepsilon$ sample complexity ($\varepsilon$SC). In contrast to prior methods, which measure the amount of information about the optimal predictor that is present in a specific amount of data, our methods measure the amount of information needed from the data to recover an approximation of the optimal predictor up to a specified tolerance. We present a framework to compare these methods based on plotting the validation loss versus training set size (the "loss-data" curve). Existing measures, such as mutual information and minimum description length probes, correspond to slices and integrals along the data-axis of the loss-data curve, while ours correspond to slices and integrals along the loss-axis. We provide experiments on real data to compare the behavior of each of these methods over datasets of varying size along with a high performance open source library for representation evaluation at https://github.com/willwhitney/reprieve.

When scaled to hundreds of billions of parameters, pretrained language models such as GPT-3 (Brown et al., 2020) achieve remarkable few-shot performance on challenging natural language understanding benchmarks. In this work, we show that performance similar to GPT-3 can be obtained with language models whose parameter count is several orders of magnitude smaller. This is achieved by converting textual inputs into cloze questions that contain some form of task description, combined with gradient-based optimization; additionally exploiting unlabeled data gives further improvements. Based on our findings, we identify several key factors required for successful natural language understanding with small language models.

This work studies the widely adopted ancestral sampling algorithms for auto-regressive language models, which is not widely studied in the literature. We use the quality-diversity (Q-D) trade-off to investigate three popular sampling algorithms (top-k, nucleus and tempered sampling). We focus on the task of open-ended language generation. We first show that the existing sampling algorithms have similar performance. After carefully inspecting the transformations defined by different sampling algorithms, we identify three key properties that are shared among them: entropy reduction, order preservation, and slope preservation. To validate the importance of the identified properties, we design two sets of new sampling algorithms: one set in which each algorithm satisfies all three properties, and one set in which each algorithm violates at least one of the properties. We compare their performance with existing sampling algorithms, and find that violating the identified properties could lead to drastic performance degradation, as measured by the Q-D trade-off. On the other hand, we find that the set of sampling algorithms that satisfies these properties performs on par with the existing sampling algorithms. Our data and code are available at https://github.com/moinnadeem/characterizing-sampling-algorithms