Sequential modelling with self-attention has achieved cutting edge performances in natural language processing. With advantages in model flexibility, computation complexity and interpretability, self-attention is gradually becoming a key component in event sequence models. However, like most other sequence models, self-attention does not account for the time span between events and thus captures sequential signals rather than temporal patterns. Without relying on recurrent network structures, self-attention recognizes event orderings via positional encoding. To bridge the gap between modelling time-independent and time-dependent event sequence, we introduce a functional feature map that embeds time span into high-dimensional spaces. By constructing the associated translation-invariant time kernel function, we reveal the functional forms of the feature map under classic functional function analysis results, namely Bochner's Theorem and Mercer's Theorem. We propose several models to learn the functional time representation and the interactions with event representation. These methods are evaluated on real-world datasets under various continuous-time event sequence prediction tasks. The experiments reveal that the proposed methods compare favorably to baseline models while also capturing useful time-event interactions.

An increase in the use of smartphones has laid to the use of the internet and social media platforms. The most commonly used social media platforms are Twitter, Facebook, WhatsApp and Instagram. People are sharing their personal experiences, reviews, feedbacks on the web. The information which is available on the web is unstructured and enormous. Hence, there is a huge scope of research on understanding the sentiment of the data available on the web. Sentiment Analysis (SA) can be carried out on the reviews, feedbacks, discussions available on the web. There has been extensive research carried out on SA in the English language, but data on the web also contains different other languages which should be analyzed. This paper aims to analyze, review and discuss the approaches, algorithms, challenges faced by the researchers while carrying out the SA on Indigenous languages.

Deploying trained convolutional neural networks (CNNs) to mobile devices is a challenging task because of the simultaneous requirements of the deployed model to be fast, lightweight and accurate. Designing and training a CNN architecture that does well on all three metrics is highly non-trivial and can be very time-consuming if done by hand. One way to solve this problem is to compress the trained CNN models before deploying to mobile devices. This work asks and answers three questions on compressing CNN models automatically: a) How to control the trade-off between speed, memory and accuracy during model compression? b) In practice, a deployed model may not see all classes and/or may not need to produce all class labels. Can this fact be used to improve the trade-off? c) How to scale the compression algorithm to execute within a reasonable amount of time for many deployments? The paper demonstrates that a model compression algorithm utilizing reinforcement learning with architecture search and knowledge distillation can answer these questions in the affirmative. Experimental results are provided for current state-of-the-art CNN model families for image feature extraction like VGG and ResNet with CIFAR datasets.

Dropout has been proven to be an effective algorithm for training robust deep networks because of its ability to prevent overfitting by avoiding the co-adaptation of feature detectors. Current explanations of dropout include bagging, naive Bayes, regularization, and sex in evolution. According to the activation patterns of neurons in the human brain, when faced with different situations, the firing rates of neurons are random and continuous, not binary as current dropout does. Inspired by this phenomenon, we extend the traditional binary dropout to continuous dropout. On the one hand, continuous dropout is considerably closer to the activation characteristics of neurons in the human brain than traditional binary dropout. On the other hand, we demonstrate that continuous dropout has the property of avoiding the co-adaptation of feature detectors, which suggests that we can extract more independent feature detectors for model averaging in the test stage. We introduce the proposed continuous dropout to a feedforward neural network and comprehensively compare it with binary dropout, adaptive dropout, and DropConnect on MNIST, CIFAR-10, SVHN, NORB, and ILSVRC-12. Thorough experiments demonstrate that our method performs better in preventing the co-adaptation of feature detectors and improves test performance. The code is available at: https://github.com/jasonustc/caffe-multigpu/tree/dropout.

Decentralized optimization algorithms have attracted intensive interests recently, as it has a balanced communication pattern, especially when solving large-scale machine learning problems. Stochastic Path Integrated Differential Estimator Stochastic First-Order method (SPIDER-SFO) nearly achieves the algorithmic lower bound in certain regimes for nonconvex problems. However, whether we can find a decentralized algorithm which achieves a similar convergence rate to SPIDER-SFO is still unclear. To tackle this problem, we propose a decentralized variant of SPIDER-SFO, called decentralized SPIDER-SFO (D-SPIDER-SFO). We show that D-SPIDER-SFO achieves a similar gradient computation cost-- that is, O ( null 3) for finding an null -approximate first-order stationary point--to its centralized counterpart. To the best of our knowledge, D-SPIDER-SFO achieves the state-of-the-art performance for solving nonconvex optimization problems on decentralized networks in terms of the computational cost. Experiments on different network configurations demonstrate the efficiency of the proposed method. Introduction Distributed optimization is a popular technique for solving large scale machine learning problems Li et al. (2014), ranging from visual object recognition Huang et al. (2017); He et al. (2016) to natural language processing V aswani et al. (2017); Devlin et al. (2019). For distributed optimization, a set of workers form a connected computational network, and each worker is assigned a portion of the computing task. The centralized network topology, like parameter server Jianmin et al. (2016); Dean et al. (2012); Li et al. (2014); Zinkevich et al. (2010), consists of a central worker connected with all other workers.

Existing generalization theories analyze the generalization performance mainly based on the model complexity and training process. The ignorance of the task properties, which results from the widely used IID assumption, makes these theories fail to interpret many generalization phenomena or guide practical learning tasks. In this paper, we propose a new Independent and Task-Identically Distributed (ITID) assumption, to consider the task properties into the data generating process. The derived generalization bound based on the ITID assumption identifies the significance of hypothesis invariance in guaranteeing generalization performance. Based on the new bound, we introduce a practical invariance enhancement algorithm from the perspective of modifying data distributions. Finally, we verify the algorithm and theorems in the context of image classification task on both toy and real-world datasets. The experimental results demonstrate the reasonableness of the ITID assumption and the effectiveness of new generalization theory in improving practical generalization performance.

Free-riders in Federated Learning: Attacks and Defenses Jierui Lin, Min Du, and Jian Liu University of California, Berkeley Abstract--Federated learning is a recently proposed paradigm that enables multiple clients to collaboratively train a joint model. It allows clients to train models locally, and leverages the parameter server to generate a global model by aggregating the locally submitted gradient updates at each round. Although the incentive model for federated learning has not been fully developed, it is supposed that participants are able to get rewards or the privilege to use the final global model, as a compensation for taking efforts to train the model. Therefore, a client who does not have any local data has the incentive to construct local gradient updates in order to deceive for rewards. In this paper, we are the first to propose the notion of free rider attacks, to explore possible ways that an attacker may construct gradient updates, without any local training data. Furthermore, we explore possible defenses that could detect the proposed attacks, and propose a new high dimensional detection method called STD-DAGMM, which particularly works well for anomaly detection of model parameters. We extend the attacks and defenses to consider more free riders as well as differential privacy, which sheds light on and calls for future research in this field. I NTRODUCTION F EDERA TED learning [1], [2], [3] has been proposed to facilitate a joint model training leveraging data from multiple clients, where the training process is coordinated by a parameter server. In the whole process, clients' data stay local, and only model parameters are communicated among clients through the parameter server. A typical training iteration works as follows. First, the parameter server sends the newest global model to each client. Then, each client locally updates the model using local data and reports updated gradients to the parameter server. Finally, the server performs model aggregation on all submitted local updates to form a new global model, which has better performance than models trained using any single client's data. Compared with an alternative approach which simply collects all data from the clients and trains a model on those data, federated learning is able to save the communication overhead by only transmitting model parameters, as well as protect privacy since all data stay local.

We investigate the convergence and stability properties of the decoupled extended Kalman filter learning algorithm (DEKF) within the long-short term memory network (LSTM) based online learning framework. For this purpose, we model DEKF as a perturbed extended Kalman filter and derive sufficient conditions for its stability during LSTM training. We show that if the perturbations -- introduced due to decoupling -- stay bounded, DEKF learns LSTM parameters with similar convergence and stability properties of the global extended Kalman filter learning algorithm. We verify our results with several numerical simulations and compare DEKF with other LSTM training methods. In our simulations, we also observe that the well-known hyper-parameter selection approaches used for DEKF in the literature satisfy our conditions.

Humans can learn a variety of concepts and skills incrementally over the course of their lives while exhibiting an array of desirable properties, such as non-forgetting, concept rehearsal, forward transfer and backward transfer of knowledge, few-shot learning, and selective forgetting. Previous approaches to lifelong machine learning can only demonstrate subsets of these properties, often by combining multiple complex mechanisms. In this Perspective, we propose a powerful unified framework that can demonstrate all of the properties by utilizing a small number of weight consolidation parameters in deep neural networks. In addition, we are able to draw many parallels between the behaviours and mechanisms of our proposed framework and those surrounding human learning, such as memory loss or sleep deprivation. This Perspective serves as a conduit for two-way inspiration to further understand lifelong learning in machines and humans.

Climate change affects occurrences of floods and droughts worldwide. However, predicting climate impacts over individual watersheds is difficult, primarily because accurate hydrological forecasts require models that are calibrated to past data. In this work we present a large-scale LSTM-based modeling approach that -- by training on large data sets -- learns a diversity of hydrological behaviors. Previous work shows that this model is more accurate than current state-of-the-art models, even when the LSTM-based approach operates out-of-sample and the latter in-sample. In this work, we show how this model can assess the sensitivity of the underlying systems with regard to extreme (high and low) flows in individual watersheds over the continental US.