Paper Group NANR 218
Model-Level Dual Learning. Plug-in Estimation in High-Dimensional Linear Inverse Problems: A Rigorous Analysis. Submodular Maximization via Gradient Ascent: The Case of Deep Submodular Functions. A novel method to determine the number of latent dimensions with SVD. UD-Japanese BCCWJ: Universal Dependencies Annotation for the Balanced Corpus of Cont …
Model-Level Dual Learning
| Title | Model-Level Dual Learning |
| Authors | Yingce Xia, Xu Tan, Fei Tian, Tao Qin, Nenghai Yu, Tie-Yan Liu |
| Abstract | Many artificial intelligence tasks appear in dual forms like English$\leftrightarrow$French translation and speech$\leftrightarrow$text transformation. Existing dual learning schemes, which are proposed to solve a pair of such dual tasks, explore how to leverage such dualities from data level. In this work, we propose a new learning framework, model-level dual learning, which takes duality of tasks into consideration while designing the architectures for the primal/dual models, and ties the model parameters that playing similar roles in the two tasks. We study both symmetric and asymmetric model-level dual learning. Our algorithms achieve significant improvements on neural machine translation and sentiment analysis. |
| Tasks | Machine Translation, Sentiment Analysis |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=2172 |
| http://proceedings.mlr.press/v80/xia18a/xia18a.pdf | |
| PWC | https://paperswithcode.com/paper/model-level-dual-learning |
| Repo | |
| Framework | |
Plug-in Estimation in High-Dimensional Linear Inverse Problems: A Rigorous Analysis
| Title | Plug-in Estimation in High-Dimensional Linear Inverse Problems: A Rigorous Analysis |
| Authors | Alyson K. Fletcher, Parthe Pandit, Sundeep Rangan, Subrata Sarkar, Philip Schniter |
| Abstract | Estimating a vector $\mathbf{x}$ from noisy linear measurements $\mathbf{Ax+w}$ often requires use of prior knowledge or structural constraints on $\mathbf{x}$ for accurate reconstruction. Several recent works have considered combining linear least-squares estimation with a generic or plug-in denoiser" function that can be designed in a modular manner based on the prior knowledge about $\mathbf{x}$. While these methods have shown excellent performance, it has been difficult to obtain rigorous performance guarantees. This work considers plug-in denoising combined with the recently-developed Vector Approximate Message Passing (VAMP) algorithm, which is itself derived via Expectation Propagation techniques. It shown that the mean squared error of this plug-in” VAMP can be exactly predicted for a large class of high-dimensional random $\Abf$ and denoisers. The method is illustrated in image reconstruction and parametric bilinear estimation. |
| Tasks | Denoising, Image Reconstruction |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/7973-plug-in-estimation-in-high-dimensional-linear-inverse-problems-a-rigorous-analysis |
| http://papers.nips.cc/paper/7973-plug-in-estimation-in-high-dimensional-linear-inverse-problems-a-rigorous-analysis.pdf | |
| PWC | https://paperswithcode.com/paper/plug-in-estimation-in-high-dimensional-linear |
| Repo | |
| Framework | |
Submodular Maximization via Gradient Ascent: The Case of Deep Submodular Functions
| Title | Submodular Maximization via Gradient Ascent: The Case of Deep Submodular Functions |
| Authors | Wenruo Bai, William Stafford Noble, Jeff A. Bilmes |
| Abstract | We study the problem of maximizing deep submodular functions (DSFs) subject to a matroid constraint. DSFs are an expressive class of submodular functions that include, as strict subfamilies, the facility location, weighted coverage, and sums of concave composed with modular functions. We use a strategy similar to the continuous greedy approach, but we show that the multilinear extension of any DSF has a natural and computationally attainable concave relaxation that we can optimize using gradient ascent. Our results show a guarantee of $\max_{0<\delta<1}(1-\epsilon-\delta-e^{-\delta^2\Omega(k)})$ with a running time of $O(\nicefrac{n^2}{\epsilon^2})$ plus time for pipage rounding to recover a discrete solution, where $k$ is the rank of the matroid constraint. This bound is often better than the standard $1-1/e$ guarantee of the continuous greedy algorithm, but runs much faster. Our bound also holds even for fully curved ($c=1$) functions where the guarantee of $1-c/e$ degenerates to $1-1/e$ where $c$ is the curvature of $f$. We perform computational experiments that support our theoretical results. |
| Tasks | |
| Published | 2018-12-01 |
| URL | http://papers.nips.cc/paper/8022-submodular-maximization-via-gradient-ascent-the-case-of-deep-submodular-functions |
| http://papers.nips.cc/paper/8022-submodular-maximization-via-gradient-ascent-the-case-of-deep-submodular-functions.pdf | |
| PWC | https://paperswithcode.com/paper/submodular-maximization-via-gradient-ascent |
| Repo | |
| Framework | |
A novel method to determine the number of latent dimensions with SVD
| Title | A novel method to determine the number of latent dimensions with SVD |
| Authors | Asana Neishabouri, Michel Desmarais |
| Abstract | Determining the number of latent dimensions is a ubiquitous problem in machine learning. In this study, we introduce a novel method that relies on SVD to discover the number of latent dimensions. The general principle behind the method is to compare the curve of singular values of the SVD decomposition of a data set with the randomized data set curve. The inferred number of latent dimensions corresponds to the crossing point of the two curves. To evaluate our methodology, we compare it with competing methods such as Kaisers eigenvalue-greater-than-one rule (K1), Parallel Analysis (PA), Velicers MAP test (Minimum Average Partial). We also compare our method with the Silhouette Width (SW) technique which is used in different clustering methods to determine the optimal number of clusters. The result on synthetic data shows that the Parallel Analysis and our method have similar results and more accurate than the other methods, and that our methods is slightly better result than the Parallel Analysis method for the sparse data sets. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=SkwAEQbAb |
| https://openreview.net/pdf?id=SkwAEQbAb | |
| PWC | https://paperswithcode.com/paper/a-novel-method-to-determine-the-number-of |
| Repo | |
| Framework | |
UD-Japanese BCCWJ: Universal Dependencies Annotation for the Balanced Corpus of Contemporary Written Japanese
| Title | UD-Japanese BCCWJ: Universal Dependencies Annotation for the Balanced Corpus of Contemporary Written Japanese |
| Authors | Mai Omura, Masayuki Asahara |
| Abstract | In this paper, we describe a corpus UD Japanese-BCCWJ that was created by converting the Balanced Corpus of Contemporary Written Japanese (BCCWJ), a Japanese language corpus, to adhere to the UD annotation schema. The BCCWJ already assigns dependency information at the level of the bunsetsu (a Japanese syntactic unit comparable to the phrase). We developed a program to convert the BCCWJ to UD based on this dependency structure, and this corpus is the result of completely automatic conversion using the program. UD Japanese-BCCWJ is the largest-scale UD Japanese corpus and the second-largest of all UD corpora, including 1,980 documents, 57,109 sentences, and 1,273k words across six distinct domains. |
| Tasks | |
| Published | 2018-11-01 |
| URL | https://www.aclweb.org/anthology/W18-6014/ |
| https://www.aclweb.org/anthology/W18-6014 | |
| PWC | https://paperswithcode.com/paper/ud-japanese-bccwj-universal-dependencies |
| Repo | |
| Framework | |
Key Protected Classification for GAN Attack Resilient Collaborative Learning
| Title | Key Protected Classification for GAN Attack Resilient Collaborative Learning |
| Authors | Mert Bülent Sarıyıldız, Ramazan Gökberk Cinbiş, Erman Ayday |
| Abstract | Large-scale publicly available datasets play a fundamental role in training deep learning models. However, large-scale datasets are difficult to collect in problems that involve processing of sensitive information. Collaborative learning techniques provide a privacy-preserving solution in such cases, by enabling training over a number of private datasets that are not shared by their owners. Existing collaborative learning techniques, combined with differential privacy, are shown to be resilient against a passive adversary which tries to infer the training data only from the model parameters. However, recently, it has been shown that the existing collaborative learning techniques are vulnerable to an active adversary that runs a GAN attack during the learning phase. In this work, we propose a novel key-based collaborative learning technique that is resilient against such GAN attacks. For this purpose, we present a collaborative learning formulation in which class scores are protected by class-specific keys, and therefore, prevents a GAN attack. We also show that very high dimensional class-specific keys can be utilized to improve robustness against attacks, without increasing the model complexity. Our experimental results on two popular datasets, MNIST and AT&T Olivetti Faces, demonstrate the effectiveness of the proposed technique against the GAN attack. To the best of our knowledge, the proposed approach is the first collaborative learning formulation that effectively tackles an active adversary, and, unlike model corruption or differential privacy formulations, our approach does not inherently feature a trade-off between model accuracy and data privacy. |
| Tasks | |
| Published | 2018-01-01 |
| URL | https://openreview.net/forum?id=Sk1NTfZAb |
| https://openreview.net/pdf?id=Sk1NTfZAb | |
| PWC | https://paperswithcode.com/paper/key-protected-classification-for-gan-attack |
| Repo | |
| Framework | |
Fine-grained Structure-based News Genre Categorization
| Title | Fine-grained Structure-based News Genre Categorization |
| Authors | Zeyu Dai, Himanshu Taneja, Ruihong Huang |
| Abstract | Journalists usually organize and present the contents of a news article following a well-defined structure. In this work, we propose a new task to categorize news articles based on their content presentation structures, which is beneficial for various NLP applications. We first define a small set of news elements considering their functions (e.g., \textit{introducing the main story or event, catching the reader{'}s attention} and \textit{providing details}) in a news story and their writing style (\textit{narrative} or \textit{expository}), and then formally define four commonly used news article structures based on their selections and organizations of news elements. We create an annotated dataset for structure-based news genre identification, and finally, we build a predictive model to assess the feasibility of this classification task using structure indicative features. |
| Tasks | Question Answering |
| Published | 2018-08-01 |
| URL | https://www.aclweb.org/anthology/W18-4308/ |
| https://www.aclweb.org/anthology/W18-4308 | |
| PWC | https://paperswithcode.com/paper/fine-grained-structure-based-news-genre |
| Repo | |
| Framework | |
Alternating-Stereo VINS: Observability Analysis and Performance Evaluation
| Title | Alternating-Stereo VINS: Observability Analysis and Performance Evaluation |
| Authors | Mrinal K. Paul, Stergios I. Roumeliotis |
| Abstract | One approach to improve the accuracy and robustness of vision-aided inertial navigation systems (VINS) that employ low-cost inertial sensors, is to obtain scale information from stereoscopic vision. Processing images from two cameras, however, is computationally expensive and increases latency. To address this limitation, in this work, a novel two-camera alternating-stereo VINS is presented. Specifically, the proposed system triggers the left-right cameras in an alternating fashion, estimates the poses corresponding to the left camera only, and introduces a linear interpolation model for processing the alternating right camera measurements. Although not a regular stereo system, the alternating visual observations when employing the proposed interpolation scheme, still provide scale information, as shown by analyzing the observability properties of the vision-only corresponding system. Finally, the performance gain, of the proposed algorithm over its monocular and stereo counterparts is assessed using various datasets. |
| Tasks | |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Paul_Alternating-Stereo_VINS_Observability_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Paul_Alternating-Stereo_VINS_Observability_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/alternating-stereo-vins-observability |
| Repo | |
| Framework | |
Generating Feedback for English Foreign Language Exercises
| Title | Generating Feedback for English Foreign Language Exercises |
| Authors | Bj{"o}rn Rudzewitz, Ramon Ziai, Kordula De Kuthy, Verena M{"o}ller, Florian Nuxoll, Detmar Meurers |
| Abstract | While immediate feedback on learner language is often discussed in the Second Language Acquisition literature (e.g., Mackey 2006), few systems used in real-life educational settings provide helpful, metalinguistic feedback to learners. In this paper, we present a novel approach leveraging task information to generate the expected range of well-formed and ill-formed variability in learner answers along with the required diagnosis and feedback. We combine this offline generation approach with an online component that matches the actual student answers against the pre-computed hypotheses. The results obtained for a set of 33 thousand answers of 7th grade German high school students learning English show that the approach successfully covers frequent answer patterns. At the same time, paraphrases and content errors require a more flexible alignment approach, for which we are planning to complement the method with the CoMiC approach successfully used for the analysis of reading comprehension answers (Meurers et al., 2011). |
| Tasks | Language Acquisition, Reading Comprehension |
| Published | 2018-06-01 |
| URL | https://www.aclweb.org/anthology/W18-0513/ |
| https://www.aclweb.org/anthology/W18-0513 | |
| PWC | https://paperswithcode.com/paper/generating-feedback-for-english-foreign |
| Repo | |
| Framework | |
Panoptic Segmentation with an End-to-End Cell R-CNN for Pathology Image Analysis
| Title | Panoptic Segmentation with an End-to-End Cell R-CNN for Pathology Image Analysis |
| Authors | Donghao Zhang, Yang Song, Dongnan Liu, Haozhe Jia, Siqi Liu, Yong Xia, Heng Huang, Weidong Cai |
| Abstract | The morphological clues of various cancer cells are essential for pathologists to determine the stages of cancers. In order to obtain the quantitative morphological information, we present an end-to-end network for panoptic segmentation of pathology images. Recently, many methods have been proposed, focusing on the semantic-level or instance-level cell segmentation. Unlike existing cell segmentation methods, the proposed network unifies detecting, localizing objects and assigning pixel-level class information to regions with large overlaps such as the background. This unifier is obtained by optimizing the novel semantic loss, the bounding box loss of Region Proposal Network (RPN), the classifier loss of RPN, the background-foreground classifier loss of segmentation Head instead of class-specific loss, the bounding box loss of proposed cell object, and the mask loss of cell object. The results demonstrate that the proposed method not only outperforms state-of-the-art approaches to the 2017 MICCAI Digital Pathology Challenge dataset, but also proposes an effective and end-to-end solution for the panoptic segmentation challenge. |
| Tasks | Cell Segmentation, Nuclear Segmentation, Panoptic Segmentation |
| Published | 2018-09-28 |
| URL | https://doi.org/10.1007/978-3-030-00934-2_27 |
| https://www.semanticscholar.org/paper/Panoptic-Segmentation-with-an-End-to-End-Cell-R-CNN-Zhang-Song/be403b1a9fa44c860044e79b8d9704cc0b217417 | |
| PWC | https://paperswithcode.com/paper/panoptic-segmentation-with-an-end-to-end-cell |
| Repo | |
| Framework | |
A Memory Network Approach for Story-Based Temporal Summarization of 360° Videos
| Title | A Memory Network Approach for Story-Based Temporal Summarization of 360° Videos |
| Authors | Sangho Lee, Jinyoung Sung, Youngjae Yu, Gunhee Kim |
| Abstract | We address the problem of story-based temporal summarization of long 360° videos. We propose a novel memory network model named Past-Future Memory Network (PFMN), in which we first compute the scores of 81 normal field of view (NFOV) region proposals cropped from the input 360° video, and then recover a latent, collective summary using the network with two external memories that store the embeddings of previously selected subshots and future candidate subshots. Our major contributions are two-fold. First, our work is the first to address story-based temporal summarization of 360° videos. Second, our model is the first attempt to leverage memory networks for video summarization tasks. For evaluation, we perform three sets of experiments. First, we investigate the view selection capability of our model on the Pano2Vid dataset. Second, we evaluate the temporal summarization with a newly collected 360° video dataset. Finally, we experiment our model’s performance in another domain, with image-based storytelling VIST dataset. We verify that our model achieves state-of-the-art performance on all the tasks. |
| Tasks | Video Summarization |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Lee_A_Memory_Network_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Lee_A_Memory_Network_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/a-memory-network-approach-for-story-based-1 |
| Repo | |
| Framework | |
Information Theoretic Guarantees for Empirical Risk Minimization with Applications to Model Selection and Large-Scale Optimization
| Title | Information Theoretic Guarantees for Empirical Risk Minimization with Applications to Model Selection and Large-Scale Optimization |
| Authors | Ibrahim Alabdulmohsin |
| Abstract | In this paper, we derive bounds on the mutual information of the empirical risk minimization (ERM) procedure for both 0-1 and strongly-convex loss classes. We prove that under the Axiom of Choice, the existence of an ERM learning rule with a vanishing mutual information is equivalent to the assertion that the loss class has a finite VC dimension, thus bridging information theory with statistical learning theory. Similarly, an asymptotic bound on the mutual information is established for strongly-convex loss classes in terms of the number of model parameters. The latter result rests on a central limit theorem (CLT) that we derive in this paper. In addition, we use our results to analyze the excess risk in stochastic convex optimization and unify previous works. Finally, we present two important applications. First, we show that the ERM of strongly-convex loss classes can be trivially scaled to big data using a naive parallelization algorithm with provable guarantees. Second, we propose a simple information criterion for model selection and demonstrate experimentally that it outperforms the popular Akaike’s information criterion (AIC) and Schwarz’s Bayesian information criterion (BIC). |
| Tasks | Model Selection |
| Published | 2018-07-01 |
| URL | https://icml.cc/Conferences/2018/Schedule?showEvent=1914 |
| http://proceedings.mlr.press/v80/alabdulmohsin18a/alabdulmohsin18a.pdf | |
| PWC | https://paperswithcode.com/paper/information-theoretic-guarantees-for |
| Repo | |
| Framework | |
Learning Multi-Instance Enriched Image Representations via Non-Greedy Ratio Maximization of the l1-Norm Distances
| Title | Learning Multi-Instance Enriched Image Representations via Non-Greedy Ratio Maximization of the l1-Norm Distances |
| Authors | Kai Liu, Hua Wang, Feiping Nie, Hao Zhang |
| Abstract | Multi-instance learning (MIL) has demonstrated its usefulness in many real-world image applications in recent years. However, two critical challenges prevent one from effectively using MIL in practice. First, existing MIL methods routinely model the predictive targets using the instances of input images, but rarely utilize an input image as a whole. As a result, the useful information conveyed by the holistic representation of an input image could be potentially lost. Second, the varied numbers of the instances of the input images in a data set make it infeasible to use traditional learning models that can only deal with single-vector inputs. To tackle these two challenges, in this paper we propose a novel image representation learning method that can integrate the local patches (the instances) of an input image (the bag) and its holistic representation into one single-vector representation. Our new method first learns a projection to preserve both global and local consistencies of the instances of an input image. It then projects the holistic representation of the same image into the learned subspace for information enrichment. Taking into account the content and characterization variations in natural scenes and photos, we develop an objective that maximizes the ratio of the summations of a number of L1-norm distances, which is difficult to solve in general. To solve our objective, we derive a new efficient non-greedy iterative algorithm and rigorously prove its convergence. Promising results in extensive experiments have demonstrated improved performances of our new method that validate its effectiveness. |
| Tasks | Representation Learning |
| Published | 2018-06-01 |
| URL | http://openaccess.thecvf.com/content_cvpr_2018/html/Liu_Learning_Multi-Instance_Enriched_CVPR_2018_paper.html |
| http://openaccess.thecvf.com/content_cvpr_2018/papers/Liu_Learning_Multi-Instance_Enriched_CVPR_2018_paper.pdf | |
| PWC | https://paperswithcode.com/paper/learning-multi-instance-enriched-image |
| Repo | |
| Framework | |
Automatic Identification of Research Fields in Scientific Papers
| Title | Automatic Identification of Research Fields in Scientific Papers |
| Authors | Eric Kergosien, Amin Farvardin, Maguelonne Teisseire, Marie-No{"e}lle Bessagnet, Joachim Sch{"o}pfel, St{'e}phane Chaudiron, Bernard Jacquemin, Annig Lacayrelle, Mathieu Roche, Christian Sallaberry, Jean Philippe Tonneau |
| Abstract | |
| Tasks | Information Retrieval |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1299/ |
| https://www.aclweb.org/anthology/L18-1299 | |
| PWC | https://paperswithcode.com/paper/automatic-identification-of-research-fields |
| Repo | |
| Framework | |
Building a Macro Chinese Discourse Treebank
| Title | Building a Macro Chinese Discourse Treebank |
| Authors | Xiaomin Chu, Feng Jiang, Sheng Xu, Qiaoming Zhu |
| Abstract | |
| Tasks | Information Retrieval, Machine Translation |
| Published | 2018-05-01 |
| URL | https://www.aclweb.org/anthology/L18-1302/ |
| https://www.aclweb.org/anthology/L18-1302 | |
| PWC | https://paperswithcode.com/paper/building-a-macro-chinese-discourse-treebank |
| Repo | |
| Framework | |
