The emerging concern about data privacy and security has motivated the proposal of federated learning, which allows nodes to only synchronize the locally-trained models instead their own original data. Conventional federated learning architecture, inherited from the parameter server design, relies on highly centralized topologies and the assumption of large nodes-to-server bandwidths. However, in real-world federated learning scenarios the network capacities between nodes are highly uniformly distributed and smaller than that in a dat-acenter. It is of great challenges for conventional federated learning approaches to efficiently utilize network capacities between nodes. In this paper, we propose a model segment level decentralized federated learning to tackle this problem. In particular, we propose a segmented gossip approach, which not only makes full utilization of node-to- node bandwidth, but also has good training convergence. The experimental results show that even the training time can be highly reduced as compared to centralized federated learning.

One of the first things to do while planning a trip is to book a good place to stay. Booking a hotel online can be an overwhelming task with thousands of hotels to choose from, for every destination. Motivated by the importance of these situations, we decided to work on the task of recommending hotels to users. W e used Expedia's hotel recommendation dataset, which has a variety of features that helped us achieve a deep understanding of the process that makes a user choose certain hotels over others. The aim of this hotel recommendation task is to predict and recommend five hotel clusters to a user that he/she is more likely to book given hundred distinct clusters.

--Deep clustering has increasingly been demonstrating superiority over conventional shallow clustering algorithms. Deep clustering algorithms usually combine representation learning with deep neural networks to achieve this performance, typically optimizing a clustering and non-clustering loss. In such cases, an autoencoder is typically connected with a clustering network, and the final clustering is jointly learned by both the autoencoder and clustering network. Instead, we propose to learn an autoencoded embedding and then search this further for the underlying manifold. We study a number of local and global manifold learning methods on both the raw data and autoencoded embedding, concluding that UMAP in our framework is able to find the best clusterable manifold of the embedding. This suggests that local manifold learning on an autoencoded embedding is effective for discovering higher quality clusters. We quantitatively show across a range of image and time-series datasets that our method has competitive performance against the latest deep clustering algorithms, including outperforming current state-of-the-art on several. We postulate that these results show a promising research direction for deep clustering. Clustering is a fundamental pillar of unsupervised machine learning. It is widely used in a range of tasks across disciplines and well-known algorithms such as k -means have found success in many applications.

Interference effects of tall buildings have attracted numerous studies due to the boom of clusters of tall buildings in megacities. To fully understand the interference effects of buildings, it often requires a substantial amount of wind tunnel tests. Limited wind tunnel tests that only cover part of interference scenarios are unable to fully reveal the interference effects. This study used machine learning techniques to resolve the conflicting requirement between limited wind tunnel tests that produce unreliable results and a completed investigation of the interference effects that is costly and time-consuming. Four machine learning models including decision tree, random forest, XGBoost, generative adversarial networks (GANs), were trained based on 30% of a dataset to predict both mean and fluctuating pressure coefficients on the principal building. The GANs model exhibited the best performance in predicting these pressure coefficients. A number of GANs models were then trained based on different portions of the dataset ranging from 10% to 90%. It was found that the GANs model based on 30% of the dataset is capable of predicting both mean and fluctuating pressure coefficients under unseen interference conditions accurately. By using this GANs model, 70% of the wind tunnel test cases can be saved, largely alleviating the cost of this kind of wind tunnel testing study.

Transfer learning enhances learning across tasks, by leveraging previously learned representations -- if they are properly chosen. We describe an efficient method to accurately estimate the appropriateness of a previously trained model for use in a new learning task. We use this measure, which we call "Predict To Learn" ("P2L"), in the two very different domains of images and semantic relations, where it predicts, from a set of "source" models, the one model most likely to produce effective transfer for training a given "target" model. We validate our approach thoroughly, by assembling a collection of candidate source models, then fine-tuning each candidate to perform each of a collection of target tasks, and finally measuring how well transfer has been enhanced. Across 95 tasks within multiple domains (images classification and semantic relations), the P2L approach was able to select the best transfer learning model on average, while the heuristic of choosing model trained with the largest data set selected the best model in only 55 cases. These results suggest that P2L captures important information in common between source and target tasks, and that this shared informational structure contributes to successful transfer learning more than simple data size.

Stochastic Gradient Descent (SGD) methods are prominent for training machine learning and deep learning models. The performance of these techniques depends on their hyperparameter tuning over time and varies for different models and problems. Manual adjustment of hyperparameters is very costly and time-consuming, and even if done correctly, it lacks theoretical justification which inevitably leads to "rule of thumb" settings. In this paper, we propose a generic approach that utilizes the statistics of an unbiased gradient estimator to automatically and simultaneously adjust two paramount hyperparameters: the learning rate and momentum. We deploy the proposed general technique for various SGD methods to train Convolutional Neural Networks (CNN's). The results match the performance of the best settings obtained through an exhaustive search and therefore, removes the need for a tedious manual tuning.

Selecting ad creative is one of the most important task for DSPs (Demand-Side Platform) in online advertising. DSPs should not only consider the effectiveness of the ad creative but also the user's psychological status when selecting ad creative. In this study, we propose an efficient and easy-to-implement ad creative selection algorithm that explicitly considers wear-in and wear-out effects of ad creative due to the repetitive ad exposures. The proposed system was deployed in a real-world production environment and tested against the baseline. It out-performed the existing system in most of the KPIs.

Representation learning has recently been successfully used to create vector representations of entities in language learning, recommender systems and in similarity learning. Graph embeddings exploit the locality structure of a graph and generate embeddings for nodes which could be words in a language, products of a retail website; and the nodes are connected based on a context window. In this paper, we consider graph embeddings with an error-free (errorless) associative learning update rule, which models the embedding vector of node as a non-convex Gaussian mixture of the embeddings of the nodes in its immediate vicinity with some constant variance that is reduced as iterations progress. It is very easy to parallelize our algorithm without any form of shared memory, which makes it possible to use it on very large graphs with a much higher dimensionality of the embeddings. Results show that our algorithm performs well when the dimensionality of the embeddings is large.

Privacy preserving machine learning algorithms are crucial for learning models over user data to protect sensitive information. Motivated by this, differentially private stochastic gradient descent (SGD) algorithms for training machine learning models have been proposed. At each step, these algorithms modify the gradients and add noise proportional to the sensitivity of the modified gradients. Under this framework, we propose AdaCliP, a theoretically motivated differentially private SGD algorithm that provably adds less noise compared to the previous methods, by using coordinate-wise adaptive clipping of the gradient. We empirically demonstrate that AdaCliP reduces the amount of added noise and produces models with better accuracy.

Pre-season prediction of crop production outcomes such as grain yields and N losses can provide insights to stakeholders when making decisions. Simulation models can assist in scenario planning, but their use is limited because of data requirements and long run times. Thus, there is a need for more computationally expedient approaches to scale up predictions. We evaluated the potential of five machine learning (ML) algorithms as meta-models for a cropping systems simulator (APSIM) to inform future decision-support tool development. We asked: 1) How well do ML meta-models predict maize yield and N losses using pre-season information? 2) How many data are needed to train ML algorithms to achieve acceptable predictions?; 3) Which input data variables are most important for accurate prediction?; and 4) Do ensembles of ML meta-models improve prediction? The simulated dataset included more than 3 million genotype, environment and management scenarios. Random forests most accurately predicted maize yield and N loss at planting time, with a RRMSE of 14% and 55%, respectively. ML meta-models reasonably reproduced simulated maize yields but not N loss. They also differed in their sensitivities to the size of the training dataset. Across all ML models, yield prediction error decreased by 10-40% as the training dataset increased from 0.5 to 1.8 million data points, whereas N loss prediction error showed no consistent pattern. ML models also differed in their sensitivities to input variables. Averaged across all ML models, weather conditions, soil properties, management information and initial conditions were roughly equally important when predicting yields. Modest prediction improvements resulted from ML ensembles. These results can help accelerate progress in coupling simulation models and ML toward developing dynamic decision support tools for pre-season management.