Paper Group ANR 411
Controlling biases and diversity in diverse image-to-image translation. Simple and Almost Assumption-Free Out-of-Sample Bound for Random Feature Mapping. Great New Design: How Do We Talk about Media Architecture in Social Media. Learning Representations and Agents for Information Retrieval. Chinese Embedding via Stroke and Glyph Information: A Dual …
Controlling biases and diversity in diverse image-to-image translation
| Title | Controlling biases and diversity in diverse image-to-image translation |
| Authors | Yaxing Wang, Abel Gonzalez-Garcia, Joost van de Weijer, Luis Herranz |
| Abstract | The task of unpaired image-to-image translation is highly challenging due to the lack of explicit cross-domain pairs of instances. We consider here diverse image translation (DIT), an even more challenging setting in which an image can have multiple plausible translations. This is normally achieved by explicitly disentangling content and style in the latent representation and sampling different styles codes while maintaining the image content. Despite the success of current DIT models, they are prone to suffer from bias. In this paper, we study the problem of bias in image-to-image translation. Biased datasets may add undesired changes (e.g. change gender or race in face images) to the output translations as a consequence of the particular underlying visual distribution in the target domain. In order to alleviate the effects of this problem we propose the use of semantic constraints that enforce the preservation of desired image properties. Our proposed model is a step towards unbiased diverse image-to-image translation (UDIT), and results in less unwanted changes in the translated images while still performing the wanted transformation. Experiments on several heavily biased datasets show the effectiveness of the proposed techniques in different domains such as faces, objects, and scenes. |
| Tasks | Image-to-Image Translation |
| Published | 2019-07-23 |
| URL | https://arxiv.org/abs/1907.09754v1 |
| https://arxiv.org/pdf/1907.09754v1.pdf | |
| PWC | https://paperswithcode.com/paper/controlling-biases-and-diversity-in-diverse |
| Repo | |
| Framework | |
Simple and Almost Assumption-Free Out-of-Sample Bound for Random Feature Mapping
| Title | Simple and Almost Assumption-Free Out-of-Sample Bound for Random Feature Mapping |
| Authors | Shusen Wang |
| Abstract | Random feature mapping (RFM) is a popular method for speeding up kernel methods at the cost of losing a little accuracy. We study kernel ridge regression with random feature mapping (RFM-KRR) and establish novel out-of-sample error upper and lower bounds. While out-of-sample bounds for RFM-KRR have been established by prior work, this paper’s theories are highly interesting for two reasons. On the one hand, our theories are based on weak and valid assumptions. In contrast, the existing theories are based on various uncheckable assumptions, which makes it unclear whether their bounds are the nature of RFM-KRR or simply the consequence of strong assumptions. On the other hand, our analysis is completely based on elementary linear algebra and thereby easy to read and verify. Finally, our experiments lend empirical supports to the theories. |
| Tasks | |
| Published | 2019-09-24 |
| URL | https://arxiv.org/abs/1909.11207v1 |
| https://arxiv.org/pdf/1909.11207v1.pdf | |
| PWC | https://paperswithcode.com/paper/simple-and-almost-assumption-free-out-of |
| Repo | |
| Framework | |
Great New Design: How Do We Talk about Media Architecture in Social Media
| Title | Great New Design: How Do We Talk about Media Architecture in Social Media |
| Authors | Selena Savic |
| Abstract | In social media, we communicate through pictures, videos, short codes, links, partial phrases. It is a rich, and digitally documented communication channel that relies on a multitude of media and forms. These channels are sorted by algorithms as organizers of discourse, mostly with the goal of channeling attention. In this research, we used Twitter to study the way Media Architecture is discussed within the community of architects, designers, researchers and policy makers. We look at the way they spontaneously share opinions on their engagement with digital infrastructures, networked places and hybrid public spaces. What can we do with all those opinions? We propose here the use of text-mining and machine learning techniques to identify important concepts and patterns in this prolific communication stream. We discuss how such techniques could inform the practice and emergence of future trends. |
| Tasks | |
| Published | 2019-10-31 |
| URL | https://arxiv.org/abs/1910.14395v1 |
| https://arxiv.org/pdf/1910.14395v1.pdf | |
| PWC | https://paperswithcode.com/paper/great-new-design-how-do-we-talk-about-media |
| Repo | |
| Framework | |
Learning Representations and Agents for Information Retrieval
| Title | Learning Representations and Agents for Information Retrieval |
| Authors | Rodrigo Nogueira |
| Abstract | A goal shared by artificial intelligence and information retrieval is to create an oracle, that is, a machine that can answer our questions, no matter how difficult they are. A more limited, but still instrumental, version of this oracle is a question-answering system, in which an open-ended question is given to the machine, and an answer is produced based on the knowledge it has access to. Such systems already exist and are increasingly capable of answering complicated questions. This progress can be partially attributed to the recent success of machine learning and to the efficient methods for storing and retrieving information, most notably through web search engines. One can imagine that this general-purpose question-answering system can be built as a billion-parameters neural network trained end-to-end with a large number of pairs of questions and answers. We argue, however, that although this approach has been very successful for tasks such as machine translation, storing the world’s knowledge as parameters of a learning machine can be very hard. A more efficient way is to train an artificial agent on how to use an external retrieval system to collect relevant information. This agent can leverage the effort that has been put into designing and running efficient storage and retrieval systems by learning how to best utilize them to accomplish a task. … |
| Tasks | Information Retrieval, Machine Translation, Question Answering |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.06132v1 |
| https://arxiv.org/pdf/1908.06132v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-representations-and-agents-for |
| Repo | |
| Framework | |
Chinese Embedding via Stroke and Glyph Information: A Dual-channel View
| Title | Chinese Embedding via Stroke and Glyph Information: A Dual-channel View |
| Authors | Hanqing Tao, Shiwei Tong, Tong Xu, Qi Liu, Enhong Chen |
| Abstract | Recent studies have consistently given positive hints that morphology is helpful in enriching word embeddings. In this paper, we argue that Chinese word embeddings can be substantially enriched by the morphological information hidden in characters which is reflected not only in strokes order sequentially, but also in character glyphs spatially. Then, we propose a novel Dual-channel Word Embedding (DWE) model to realize the joint learning of sequential and spatial information of characters. Through the evaluation on both word similarity and word analogy tasks, our model shows its rationality and superiority in modelling the morphology of Chinese. |
| Tasks | Word Embeddings |
| Published | 2019-06-03 |
| URL | https://arxiv.org/abs/1906.04287v1 |
| https://arxiv.org/pdf/1906.04287v1.pdf | |
| PWC | https://paperswithcode.com/paper/chinese-embedding-via-stroke-and-glyph |
| Repo | |
| Framework | |
Improving Channel Charting with Representation-Constrained Autoencoders
| Title | Improving Channel Charting with Representation-Constrained Autoencoders |
| Authors | Pengzhi Huang, Oscar Castañeda, Emre Gönültaş, Saïd Medjkouh, Olav Tirkkonen, Tom Goldstein, Christoph Studer |
| Abstract | Channel charting (CC) has been proposed recently to enable logical positioning of user equipments (UEs) in the neighborhood of a multi-antenna base-station solely from channel-state information (CSI). CC relies on dimensionality reduction of high-dimensional CSI features in order to construct a channel chart that captures spatial and radio geometries so that UEs close in space are close in the channel chart. In this paper, we demonstrate that autoencoder (AE)-based CC can be augmented with side information that is obtained during the CSI acquisition process. More specifically, we propose to include pairwise representation constraints into AEs with the goal of improving the quality of the learned channel charts. We show that such representation-constrained AEs recover the global geometry of the learned channel charts, which enables CC to perform approximate positioning without global navigation satellite systems or supervised learning methods that rely on extensive and expensive measurement campaigns. |
| Tasks | Dimensionality Reduction |
| Published | 2019-08-07 |
| URL | https://arxiv.org/abs/1908.02878v1 |
| https://arxiv.org/pdf/1908.02878v1.pdf | |
| PWC | https://paperswithcode.com/paper/improving-channel-charting-with |
| Repo | |
| Framework | |
Towards a Forensic Event Ontology to Assist Video Surveillance-based Vandalism Detection
| Title | Towards a Forensic Event Ontology to Assist Video Surveillance-based Vandalism Detection |
| Authors | Faranak Sobhani, Umberto Straccia |
| Abstract | The detection and representation of events is a critical element in automated surveillance systems. We present here an ontology for representing complex semantic events to assist video surveillance-based vandalism detection. The ontology contains the definition of a rich and articulated event vocabulary that is aimed at aiding forensic analysis to objectively identify and represent complex events. Our ontology has then been applied in the context of London Riots, which took place in 2011. We report also on the experiments conducted to support the classification of complex criminal events from video data. |
| Tasks | |
| Published | 2019-03-21 |
| URL | http://arxiv.org/abs/1903.09012v1 |
| http://arxiv.org/pdf/1903.09012v1.pdf | |
| PWC | https://paperswithcode.com/paper/towards-a-forensic-event-ontology-to-assist |
| Repo | |
| Framework | |
Inferring the Importance of Product Appearance: A Step Towards the Screenless Revolution
| Title | Inferring the Importance of Product Appearance: A Step Towards the Screenless Revolution |
| Authors | Yongshun Gong, Jinfeng Yi, Dongdong Chen, Jian Zhang, Jiayu Zhou, Zhihua Zhou |
| Abstract | Nowadays, almost all the online orders were placed through screened devices such as mobile phones, tablets, and computers. With the rapid development of the Internet of Things (IoT) and smart appliances, more and more screenless smart devices, e.g., smart speaker and smart refrigerator, appear in our daily lives. They open up new means of interaction and may provide an excellent opportunity to reach new customers and increase sales. However, not all the items are suitable for screenless shopping, since some items’ appearance play an important role in consumer decision making. Typical examples include clothes, dolls, bags, and shoes. In this paper, we aim to infer the significance of every item’s appearance in consumer decision making and identify the group of items that are suitable for screenless shopping. Specifically, we formulate the problem as a classification task that predicts if an item’s appearance has a significant impact on people’s purchase behavior. To solve this problem, we extract features from three different views, namely items’ intrinsic properties, items’ images, and users’ comments, and collect a set of necessary labels via crowdsourcing. We then propose an iterative semi-supervised learning framework with three carefully designed loss functions. We conduct extensive experiments on a real-world transaction dataset collected from the online retail giant JD.com. Experimental results verify the effectiveness of the proposed method. |
| Tasks | Decision Making |
| Published | 2019-05-01 |
| URL | https://arxiv.org/abs/1905.03698v2 |
| https://arxiv.org/pdf/1905.03698v2.pdf | |
| PWC | https://paperswithcode.com/paper/190503698 |
| Repo | |
| Framework | |
AIBench: An Industry Standard Internet Service AI Benchmark Suite
| Title | AIBench: An Industry Standard Internet Service AI Benchmark Suite |
| Authors | Wanling Gao, Fei Tang, Lei Wang, Jianfeng Zhan, Chunxin Lan, Chunjie Luo, Yunyou Huang, Chen Zheng, Jiahui Dai, Zheng Cao, Daoyi Zheng, Haoning Tang, Kunlin Zhan, Biao Wang, Defei Kong, Tong Wu, Minghe Yu, Chongkang Tan, Huan Li, Xinhui Tian, Yatao Li, Junchao Shao, Zhenyu Wang, Xiaoyu Wang, Hainan Ye |
| Abstract | Today’s Internet Services are undergoing fundamental changes and shifting to an intelligent computing era where AI is widely employed to augment services. In this context, many innovative AI algorithms, systems, and architectures are proposed, and thus the importance of benchmarking and evaluating them rises. However, modern Internet services adopt a microservice-based architecture and consist of various modules. The diversity of these modules and complexity of execution paths, the massive scale and complex hierarchy of datacenter infrastructure, the confidential issues of data sets and workloads pose great challenges to benchmarking. In this paper, we present the first industry-standard Internet service AI benchmark suite—AIBench with seventeen industry partners, including several top Internet service providers. AIBench provides a highly extensible, configurable, and flexible benchmark framework that contains loosely coupled modules. We identify sixteen prominent AI problem domains like learning to rank, each of which forms an AI component benchmark, from three most important Internet service domains: search engine, social network, and e-commerce, which is by far the most comprehensive AI benchmarking effort. On the basis of the AIBench framework, abstracting the real-world data sets and workloads from one of the top e-commerce providers, we design and implement the first end-to-end Internet service AI benchmark, which contains the primary modules in the critical paths of an industry scale application and is scalable to deploy on different cluster scales. The specifications, source code, and performance numbers are publicly available from the benchmark council web site http://www.benchcouncil.org/AIBench/index.html. |
| Tasks | Learning-To-Rank |
| Published | 2019-08-13 |
| URL | https://arxiv.org/abs/1908.08998v2 |
| https://arxiv.org/pdf/1908.08998v2.pdf | |
| PWC | https://paperswithcode.com/paper/aibench-an-industry-standard-internet-service |
| Repo | |
| Framework | |
Integrating Markov processes with structural causal modeling enables counterfactual inference in complex systems
| Title | Integrating Markov processes with structural causal modeling enables counterfactual inference in complex systems |
| Authors | Robert Osazuwa Ness, Kaushal Paneri, Olga Vitek |
| Abstract | This manuscript contributes a general and practical framework for casting a Markov process model of a system at equilibrium as a structural causal model, and carrying out counterfactual inference. Markov processes mathematically describe the mechanisms in the system, and predict the system’s equilibrium behavior upon intervention, but do not support counterfactual inference. In contrast, structural causal models support counterfactual inference, but do not identify the mechanisms. This manuscript leverages the benefits of both approaches. We define the structural causal models in terms of the parameters and the equilibrium dynamics of the Markov process models, and counterfactual inference flows from these settings. The proposed approach alleviates the identifiability drawback of the structural causal models, in that the counterfactual inference is consistent with the counterfactual trajectories simulated from the Markov process model. We showcase the benefits of this framework in case studies of complex biomolecular systems with nonlinear dynamics. We illustrate that, in presence of Markov process model misspecification, counterfactual inference leverages prior data, and therefore estimates the outcome of an intervention more accurately than a direct simulation. |
| Tasks | Counterfactual Inference |
| Published | 2019-11-06 |
| URL | https://arxiv.org/abs/1911.02175v1 |
| https://arxiv.org/pdf/1911.02175v1.pdf | |
| PWC | https://paperswithcode.com/paper/integrating-markov-processes-with-structural |
| Repo | |
| Framework | |
X-Ray Image Compression Using Convolutional Recurrent Neural Networks
| Title | X-Ray Image Compression Using Convolutional Recurrent Neural Networks |
| Authors | Asif Shahriyar Sushmit, Shakib Uz Zaman, Ahmed Imtiaz Humayun, Taufiq Hasan, Mohammed Imamul Hassan Bhuiyan |
| Abstract | In the advent of a digital health revolution, vast amounts of clinical data are being generated, stored and processed on a daily basis. This has made the storage and retrieval of large volumes of health-care data, especially, high-resolution medical images, particularly challenging. Effective image compression for medical images thus plays a vital role in today’s healthcare information system, particularly in teleradiology. In this work, an X-ray image compression method based on a Convolutional Recurrent Neural Networks RNN-Conv is presented. The proposed architecture can provide variable compression rates during deployment while it requires each network to be trained only once for a specific dimension of X-ray images. The model uses a multi-level pooling scheme that learns contextualized features for effective compression. We perform our image compression experiments on the National Institute of Health (NIH) ChestX-ray8 dataset and compare the performance of the proposed architecture with a state-of-the-art RNN based technique and JPEG 2000. The experimental results depict improved compression performance achieved by the proposed method in terms of Structural Similarity Index (SSIM) and Peak Signal-to-Noise Ratio (PSNR) metrics. To the best of our knowledge, this is the first reported evaluation on using a deep convolutional RNN for medical image compression. |
| Tasks | Image Compression |
| Published | 2019-04-28 |
| URL | https://arxiv.org/abs/1904.12271v2 |
| https://arxiv.org/pdf/1904.12271v2.pdf | |
| PWC | https://paperswithcode.com/paper/x-ray-image-compression-using-convolutional |
| Repo | |
| Framework | |
Template-Based Posit Multiplication for Training and Inferring in Neural Networks
| Title | Template-Based Posit Multiplication for Training and Inferring in Neural Networks |
| Authors | Raúl Murillo Montero, Alberto A. Del Barrio, Guillermo Botella |
| Abstract | The posit number system is arguably the most promising and discussed topic in Arithmetic nowadays. The recent breakthroughs claimed by the format proposed by John L. Gustafson have put posits in the spotlight. In this work, we first describe an algorithm for multiplying two posit numbers, even when the number of exponent bits is zero. This configuration, scarcely tackled in literature, is particularly interesting because it allows the deployment of a fast sigmoid function. The proposed multiplication algorithm is then integrated as a template into the well-known FloPoCo framework. Synthesis results are shown to compare with the floating point multiplication offered by FloPoCo as well. Second, the performance of posits is studied in the scenario of Neural Networks in both training and inference stages. To the best of our knowledge, this is the first time that training is done with posit format, achieving promising results for a binary classification problem even with reduced posit configurations. In the inference stage, 8-bit posits are as good as floating point when dealing with the MNIST dataset, but lose some accuracy with CIFAR-10. |
| Tasks | |
| Published | 2019-07-09 |
| URL | https://arxiv.org/abs/1907.04091v1 |
| https://arxiv.org/pdf/1907.04091v1.pdf | |
| PWC | https://paperswithcode.com/paper/template-based-posit-multiplication-for |
| Repo | |
| Framework | |
Discriminative Dimension Reduction based on Mutual Information
| Title | Discriminative Dimension Reduction based on Mutual Information |
| Authors | Orod Razeghi, Guoping Qiu |
| Abstract | The “curse of dimensionality” is a well-known problem in pattern recognition. A widely used approach to tackling the problem is a group of subspace methods, where the original features are projected onto a new space. The lower dimensional subspace is then used to approximate the original features for classification. However, most subspace methods were not originally developed for classification. We believe that direct adoption of these subspace methods for pattern classification should not be considered best practice. In this paper, we present a new information theory based algorithm for selecting subspaces, which can always result in superior performance over conventional methods. This paper makes the following main contributions: i) it improves a common practice widely used by practitioners in the field of pattern recognition, ii) it develops an information theory based technique for systematically selecting the subspaces that are discriminative and therefore are suitable for pattern recognition/classification purposes, iii) it presents extensive experimental results on a variety of computer vision and pattern recognition tasks to illustrate that the subspaces selected based on maximum mutual information criterion will always enhance performance regardless of the classification techniques used. |
| Tasks | Dimensionality Reduction |
| Published | 2019-12-11 |
| URL | https://arxiv.org/abs/1912.05631v1 |
| https://arxiv.org/pdf/1912.05631v1.pdf | |
| PWC | https://paperswithcode.com/paper/discriminative-dimension-reduction-based-on |
| Repo | |
| Framework | |
Counterfactual Inference for Consumer Choice Across Many Product Categories
| Title | Counterfactual Inference for Consumer Choice Across Many Product Categories |
| Authors | Rob Donnelly, Francisco R. Ruiz, David Blei, Susan Athey |
| Abstract | This paper proposes a method for estimating consumer preferences among discrete choices, where the consumer chooses at most one product in a category, but selects from multiple categories in parallel. The consumer’s utility is additive in the different categories. Her preferences about product attributes as well as her price sensitivity vary across products and are in general correlated across products. We build on techniques from the machine learning literature on probabilistic models of matrix factorization, extending the methods to account for time-varying product attributes and products going out of stock. We evaluate the performance of the model using held-out data from weeks with price changes or out of stock products. We show that our model improves over traditional modeling approaches that consider each category in isolation. One source of the improvement is the ability of the model to accurately estimate heterogeneity in preferences (by pooling information across categories); another source of improvement is its ability to estimate the preferences of consumers who have rarely or never made a purchase in a given category in the training data. Using held-out data, we show that our model can accurately distinguish which consumers are most price sensitive to a given product. We consider counterfactuals such as personally targeted price discounts, showing that using a richer model such as the one we propose substantially increases the benefits of personalization in discounts. |
| Tasks | Counterfactual Inference |
| Published | 2019-06-06 |
| URL | https://arxiv.org/abs/1906.02635v1 |
| https://arxiv.org/pdf/1906.02635v1.pdf | |
| PWC | https://paperswithcode.com/paper/counterfactual-inference-for-consumer-choice |
| Repo | |
| Framework | |
Self Organizing Nebulous Growths for Robust and Incremental Data Visualization
| Title | Self Organizing Nebulous Growths for Robust and Incremental Data Visualization |
| Authors | Damith Senanayake, Wei Wang, Shalin H. Naik, Saman Halgamuge |
| Abstract | Non-parametric dimensionality reduction techniques, such as t-SNE and UMAP, are proficient in providing visualizations for fixed or static datasets, but they cannot incrementally map and insert new data points into existing data visualizations. We present Self-Organizing Nebulous Growths (SONG), a parametric nonlinear dimensionality reduction technique that supports incremental data visualization, i.e., incremental addition of new data while preserving the structure of the existing visualization. In addition, SONG is capable of handling new data increments no matter whether they are similar or heterogeneous to the existing observations in distribution. We test SONG on a variety of real and simulated datasets. The results show that SONG is superior to Parametric t-SNE, t-SNE and UMAP in incremental data visualization. Specifically, for heterogeneous increments, SONG improves over Parametric t-SNE by 14.98 % on the Fashion MNIST dataset and 49.73% on the MNIST dataset regarding the cluster quality measured by the Adjusted Mutual Information scores. On similar or homogeneous increments, the improvements are 8.36% and 42.26% respectively. Furthermore, even in static cases, SONG performs better or comparable to UMAP, and superior to t-SNE. We also demonstrate that the algorithmic foundations of SONG render it more tolerant to noise compared to UMAP and t-SNE, thus providing greater utility for data with high variance or high mixing of clusters or noise. |
| Tasks | Dimensionality Reduction |
| Published | 2019-12-09 |
| URL | https://arxiv.org/abs/1912.04896v1 |
| https://arxiv.org/pdf/1912.04896v1.pdf | |
| PWC | https://paperswithcode.com/paper/self-organizing-nebulous-growths-for-robust |
| Repo | |
| Framework | |
