Name disambiguation aims to identify unique authors with the same name. Existing name disambiguation methods always exploit author attributes to enhance disambiguation results. However, some discriminative author attributes (e.g., email and affiliation) may change because of graduation or job-hopping, which will result in the separation of the same author's papers in digital libraries. Although these attributes may change, an author's co-authors and research topics do not change frequently with time, which means that papers within a period have similar text and relation information in the academic network. Inspired by this idea, we introduce Multi-view Attention-based Pairwise Recurrent Neural Network (MA-PairRNN) to solve the name disambiguation problem. We divided papers into small blocks based on discriminative author attributes and blocks of the same author will be merged according to pairwise classification results of MA-PairRNN. MA-PairRNN combines heterogeneous graph embedding learning and pairwise similarity learning into a framework. In addition to attribute and structure information, MA-PairRNN also exploits semantic information by meta-path and generates node representation in an inductive way, which is scalable to large graphs. Furthermore, a semantic-level attention mechanism is adopted to fuse multiple meta-path based representations. A Pseudo-Siamese network consisting of two RNNs takes two paper sequences in publication time order as input and outputs their similarity. Results on two real-world datasets demonstrate that our framework has a significant and consistent improvement of performance on the name disambiguation task. It was also demonstrated that MA-PairRNN can perform well with a small amount of training data and have better generalization ability across different research areas.

Along with the analysis of time-to-event data, it is common to assume that only partial information is given at hand. In the presence of right-censored data with covariates, the conditional Kaplan-Meier estimator (also referred as the Beran estimator) is known to propose a consistent estimate for the lifetimes conditional survival function. However, a necessary condition is the clear knowledge of whether each individual is censored or not, although, this information might be incomplete or even totally absent in practice. We thus propose a study on the Beran estimator when the censoring indicator is not clearly specified. From this, we provide a new estimator for the conditional survival function and establish its asymptotic normality under mild conditions. We further study the supervised learning problem where the conditional survival function is to be predicted with no censorship indicators. To this aim, we investigate various approaches estimating the conditional expectation for the censoring indicator. Along with the theoretical results, we illustrate how the estimators work for small samples by means of a simulation study and show their practical applicability with the analysis of synthetic data and the study of real data for the prognosis of monoclonal gammopathy.

Testing new, innovative technologies is a crucial task for safety and acceptance. But how can new systems be tested if no historical real-world data exist? Simulation provides an answer to this important question. Classical simulation tools such as event-based simulation are well accepted. But most of these established simulation models require the specification of many parameters. Furthermore, simulation runs, e.g., CFD simulations, are very time consuming. Generative Adversarial Networks (GANs) are powerful tools for generating new data for a variety of tasks. Currently, their most frequent application domain is image generation. This article investigates the applicability of GANs for imitating simulations. We are comparing the simulation output of a technical system with the output of a GAN. To exemplify this approach, a well-known multi-car elevator system simulator was chosen. Our study demonstrates the feasibility of this approach. It also discusses pitfalls and technical problems that occurred during the implementation. Although we were able to show that in principle, GANs can be used as substitutes for expensive simulation runs, we also show that they cannot be used "out of the box". Fine tuning is needed. We present a proof-of-concept, which can serve as a starting point for further research.

Unsupervised graph representation learning aims to learn low-dimensional node embeddings without supervision while preserving graph topological structures and node attributive features. Previous graph neural networks (GNN) require a large number of labeled nodes, which may not be accessible in real-world graph data. In this paper, we present a novel cluster-aware graph neural network (CAGNN) model for unsupervised graph representation learning using self-supervised techniques. In CAGNN, we perform clustering on the node embeddings and update the model parameters by predicting the cluster assignments. Moreover, we observe that graphs often contain inter-class edges, which mislead the GNN model to aggregate noisy information from neighborhood nodes. We further refine the graph topology by strengthening intra-class edges and reducing node connections between different classes based on cluster labels, which better preserves cluster structures in the embedding space. We conduct comprehensive experiments on two benchmark tasks using real-world datasets. The results demonstrate the superior performance of the proposed model over existing baseline methods. Notably, our model gains over 7% improvements in terms of accuracy on node clustering over state-of-the-arts.

Neural networks have shown high successful performance in a wide range of tasks, but further studies are needed to improve its performance. We analyze the approximation error of the specific neural network architecture with a local connection and higher application than one with the full connection because the local-connected network can be used to explain diverse neural networks such as CNNs. Our error estimate depends on two parameters: one controlling the depth of the hidden layer, and the other, the width of the hidden layers.

Training a deep neural network requires a large amount of single-task data and involves a long time-consuming optimization phase. This is not scalable to complex, realistic environments with new unexpected changes. Humans can perform fast incremental learning on the fly and memory systems in the brain play a critical role. We introduce Sparse Meta Networks -- a meta-learning approach to learn online sequential adaptation algorithms for deep neural networks, by using deep neural networks. We augment a deep neural network with a layer-specific fast-weight memory. The fast-weights are generated sparsely at each time step and accumulated incrementally through time providing a useful inductive bias for online continual adaptation. We demonstrate strong performance on a variety of sequential adaptation scenarios, from a simple online reinforcement learning to a large scale adaptive language modelling.

The ability to efficiently search for images over an indexed database is the cornerstone for several user experiences. Incorporating user feedback, through multi-modal inputs provide flexible and interaction to serve fine-grained specificity in requirements. We specifically focus on text feedback, through descriptive natural language queries. Given a reference image and textual user feedback, our goal is to retrieve images that satisfy constraints specified by both of these input modalities. The task is challenging as it requires understanding the textual semantics from the text feedback and then applying these changes to the visual representation. To address these challenges, we propose a novel architecture TRACE which contains a hierarchical feature aggregation module to learn the composite visio-linguistic representations. TRACE achieves the SOTA performance on 3 benchmark datasets: FashionIQ, Shoes, and Birds-to-Words, with an average improvement of at least ~5.7%, ~3%, and ~5% respectively in R@K metric. Our extensive experiments and ablation studies show that TRACE consistently outperforms the existing techniques by significant margins both quantitatively and qualitatively.

In late April 2020, a company named OpenAI uploaded dozens of new tracks to SoundCloud, all of them matter-of-factly titled like "Hip-hop, in the style of Nas" or "Pop, in the style of Katy Perry." You'd be forgiven for initially thinking the songs were average YouTube covers. A few seconds spent listening to the gargled production, bizarre lyrics, and eerie vocals would definitely change your mind. The songs were all made using an artificial intelligence software called Jukebox, designed by OpenAI, a billion dollar research organization leading the field in AI research. Jukebox isn't your standard Elvis impersonator: After being trained on 1.2 million songs and other data about genres and artists, the neural net has learned to produce original music in the uncannily recognizable style of famous artists like Elton John and Rihanna.

Petuum is very excited to announce the launch of our newest open source offering, AdaptDL, a resource-adaptive deep learning (DL) training and scheduling framework. The goal of AdaptDL is to make distributed DL easy and efficient in dynamic-resource environments such as shared clusters and the cloud. During our benchmark studies when using AdaptDL with Amazon Web Services (AWS), we recorded a reduction in cost by up to 80% when AdaptDL was set to automatically provision spot instances on AWS when available. AdaptDL can automatically determine the optimal number of resources given a job's need. It will efficiently add or remove resources dynamically to ensure the highest-level performance.

The press is full of articles on why businesses need AI because it is expected to make a tremendous impact. The McKinsey Global Institute estimates that by 2030, the additional annual global economic impact will be $13 trillion, a figure that equals about 62 percent of the total current U.S. GDP. Gartner estimates that by the end of 2024, 75 percent of organizations will have moved from merely piloting AI to making it operational, and AI made their list of the Gartner Top 8 Supply Chain Technology Trends for 2020. AI has made explosive progress since 2012 when a grad student from the University of Toronto won the ImageNet Challenge by a huge margin using deep learning, at the time considered a fringe method. Ever since, deep learning has taken Silicon Valley by storm, and AI has spread into all sectors, including supply chain, to address vexing problems previously considered unattainable.