We study the spectral recovery problem for dynamical sampling on a finite cyclic grid. Given time snapshots obtained from a fixed uniform spatial subsampling of the orbit $x_{\ell}=A^{\ell}f$, we aim to recover the spectrum of the unknown circular convolution operator $A$. However, in the presence of outliers, even in only a few snapshots, existing approaches often struggle to recover the spectrum. We address this challenge by proposing a novel robust spectral recovery model in the presence of time-sparse corruptions. We propose a robust pipeline that lifts the problem to a sequence of robust low-rank Hankel recovery and completion tasks, followed by Prony-type spectral estimation. Numerical experiments confirm the accurate spectral recovery of the proposed approach and exhibit its superior robustness against state-of-the-art under various settings.

This paper considers the problem of recovering signals modeled by generative models from linear measurements contaminated with sparse outliers. We propose an outlier detection approach for reconstructing the ground-truth signals by solving an$\ell _{1}$norm minimization problem. We establish theoretical recovery guarantees for reconstruction of signals using generative models in the presence of outliers, giving lower bounds on the number of correctable outliers. Our results are applicable to both linear and nonlinear generator neural networks with an arbitrary number of layers. We propose an iterative and linearized alternating direction method of multipliers (ADMM) algorithm for solving the outlier detection problem via$\ell _{1}$norm minimization, and a gradient descent algorithm for solving the outlier detection problem via squared$\ell _{1}$norm minimization. We conduct extensive experiments using variational auto-encoder and deep convolutional generative adversarial networks, and the experimental results show that the signals can be successfully reconstructed under outliers using our approach. Our approach outperforms the traditional Lasso and$\ell _{2}$norm minimization approach.

Most traffic anomaly detection systems for the Internet of Things (IoT) build detection models using features extracted from the packet header. The performance of such models may fluctuate when network conditions change over time, because some information in the packet header, e.g., the packet arrival interval, reflects the current network condition. To improve the performance of IoT anomaly detection models, we propose a content-aided approach that leverages the payload of packets, i.e., the content carried by the packets, to build a machine learning model. This approach is based on the observation that IoT devices, unlike general-purpose computers, are usually used for very specific tasks, e.g., a smart camera mainly carries video information. Our content-aided approach considers both packet header as well as payload information and ensembles two machine learning models, one built with information from packet headers and the other with information from packet payload, to obtain the final detection results. Experimental results demonstrate that our content-aided method can achieve consistent detection results of about 99% of true positive rate and about 4% false positive rate, in the presence of significant network condition changes.

In neural abstractive summarization, the generated summaries often face semantic irrelevance and content deviation from the input sentences. In this work, we incorporate semantic dependency graphs about predicate-argument structure of input sentences into neural abstractive summarization for the problem. We propose a novel semantics dependency guided summarization model (SemSUM), which can leverage the information of original input texts and the corresponding semantic dependency graphs in a complementary way to guide summarization process. We evaluate our model on the English Gigaword, DUC 2004 and MSR abstractive sentence summarization datasets. Experiments show that the proposed model improves semantic relevance and reduces content deviation, and also brings significant improvements on automatic evaluation ROUGE metrics.

In this paper, we propose a multi-granularity interaction network for extractive and abstractive multi-document summarization, which jointly learn semantic representations for words, sentences, and documents.The word representations are used to generate an abstractive summary while the sentence representations are used to produce an extractive summary.We employ attention mechanisms to interact between different granularity of semantic representations, which helps to capture multi-granularity key information and improves the performance of both abstractive and extractive summarization.Experiment results show that our proposed model substantially outperforms all strong baseline methods and achieves the best results on the Multi-News dataset.

The graph-to-sequence (Graph2Seq) learning aims to transduce graph-structured representations to word sequences for text generation.Recent studies propose various models to encode graph structure.However, most previous works ignore the indirect relations between distance nodes, or treat indirect relations and direct relations in the same way.In this paper, we propose the Heterogeneous Graph Transformer to independently model the different relations in the individual subgraphs of the original graph, including direct relations, indirect relations and multiple possible relations between nodes.Experimental results show that our model strongly outperforms the state of the art on all four standard benchmarks of AMRto-text generation and syntax-based neural machine translation.

This paper presents an observer-integrated Reinforcement Learning (RL) approach, called Disturbance OB-server Network (DOB-Net), for robots operating in environments where disturbances are unknown and time-varying, and may frequently exceed robot control capabilities. The DOB-Net integrates a disturbance dynamics observer network and a controller network. Originated from conventional DOB mechanisms, the observer is built and enhanced via Recurrent Neural Networks (RNNs), encoding estimation of past values and prediction of future values of unknown disturbances in RNN hidden state. Such encoding allows the controller generate optimal control signals to actively reject disturbances, under the constraints of robot control capabilities. The observer and the controller are jointly learned within policy optimization by advantage actor critic. Numerical simulations on position regulation tasks have demonstrated that the proposed DOB-Net significantly outperforms conventional feedback controllers and classical RL policy.

AMR-to-text generation is a challenging task of generating texts from graph-based semantic representations. Recent studies formalize this task a graph-to-sequence learning problem and use various graph neural networks to model graph structure. In this paper, we propose a novel approach that generates texts from AMR graphs while reconstructing the input graph structures. Our model employs graph attention mechanism to aggregate information for encoding the inputs. Moreover, better node representations are learned by optimizing two simple but effective auxiliary reconstruction objectives: link prediction objective which requires predicting the semantic relationship between nodes, and distance prediction objective which requires predicting the distance between nodes. Experimental results on two benchmark datasets show that our proposed model improves considerably over strong baselines and achieves new state-of-the-art.

Abstract meaning representation (AMR)-to-text generation is the challenging task of generating natural language texts from AMR graphs, where nodes represent concepts and edges denote relations. The current state-of-the-art methods use graph-to-sequence models; however, they still cannot significantly outperform the previous sequence-to-sequence models or statistical approaches. In this paper, we propose a novel graph-to-sequence model (Graph Transformer) to address this task. The model directly encodes the AMR graphs and learns the node representations. A pairwise interaction function is used for computing the semantic relations between the concepts. Moreover, attention mechanisms are used for aggregating the information from the incoming and outgoing neighbors, which help the model to capture the semantic information effectively. Our model outperforms the state-of-the-art neural approach by 1.5 BLEU points on LDC2015E86 and 4.8 BLEU points on LDC2017T10 and achieves new state-of-the-art performances.

Modeling discourse coherence is an important problem in natural language generation and understanding. Sentence ordering, the goal of which is to organize a set of sentences into a coherent text, is a commonly used task to learn and evaluate the model. In this paper, we propose a novel hierarchical attention network that captures word clues and dependencies between sentences to address this problem. Our model outperforms prior methods and achieves state-of-the-art performance on several datasets in different domains. Furthermore, our experiments demonstrate that the model performs very well even though adding noisy sentences into the set, which shows the robustness and effectiveness of the model. Visualization analysis and case study show that our model captures the structure and pattern of coherent texts not only by simple word clues but also by consecution in context.

We present a method called SketchyCoreSVD to compute the near-optimal rank r SVD of a data matrix by building random sketches only from its subsampled columns and rows. We provide theoretical guarantees under incoherence assumptions, and validate the performance of our SketchyCoreSVD method on various large static and time-varying datasets.

Story completion is a very challenging task of generating the missing plot for an incomplete story, which requires not only understanding but also inference of the given contextual clues. In this paper, we present a novel conditional variational autoencoder based on Transformer for missing plot generation. Our model uses shared attention layers for encoder and decoder, which make the most of the contextual clues, and a latent variable for learning the distribution of coherent story plots. Through drawing samples from the learned distribution, diverse reasonable plots can be generated. Both automatic and manual evaluations show that our model generates better story plots than state-of-the-art models in terms of readability, diversity and coherence.

Labeling topics learned by topic models is a challenging problem.Previous studies have used words, phrases and images to label topics.In this paper, we propose to use text summaries for topic labeling.Several sentences are extracted from the most related documents to form the summary for each topic.In order to obtain summaries with both high relevance, coverage and discrimination for all the topics, we propose an algorithm based on submodular optimization.Both automatic and manual analysis have been conducted on two real document collections, and we find 1) the summaries extracted by our proposed algorithm are superior over the summaries extracted by existing popular summarization methods; 2) the use of summaries as labels has obvious advantages over the use of words and phrases.

BACKGROUND: Owing to the rapid expansion of RNA structure databases in recent years, efficient methods for structure comparison are in demand for function prediction and evolutionary analysis. Usually, the similarity of RNA secondary structures is evaluated based on tree models and dynamic programming algorithms. We present here a new method for the similarity analysis of RNA secondary structures. RESULTS: Three sets of real data have been used as input for the example applications. Set I includes the structures from 5S rRNAs. Set II includes the secondary structures from RNase P and RNase MRP. Set III includes the structures from 16S rRNAs. Reasonable phylogenetic trees are derived for these three sets of data by using our method. Moreover, our program runs faster as compared to some existing ones. CONCLUSION: The famous Lempel-Ziv algorithm can efficiently extract the information on repeated patterns encoded in RNA secondary structures and makes our method an alternative to analyze the similarity of RNA secondary structures. This method will also be useful to researchers who are interested in evolutionary analysis.