Paper Group ANR 1477
Linear Bandits with Feature Feedback. Efficient Automatic Meta Optimization Search for Few-Shot Learning. Predicting Patent Citations to measure Economic Impact of Scholarly Research. TrendNets: Mapping Emerging Research Trends From Dynamic Co-Word Networks via Sparse Representation. Adaptive Reduced Rank Regression. NeuroMask: Explaining Predictio …
Linear Bandits with Feature Feedback
| Title | Linear Bandits with Feature Feedback |
| Authors | Urvashi Oswal, Aniruddha Bhargava, Robert Nowak |
| Abstract | This paper explores a new form of the linear bandit problem in which the algorithm receives the usual stochastic rewards as well as stochastic feedback about which features are relevant to the rewards, the latter feedback being the novel aspect. The focus of this paper is the development of new theory and algorithms for linear bandits with feature feedback. We show that linear bandits with feature feedback can achieve regret over time horizon $T$ that scales like $k\sqrt{T}$, without prior knowledge of which features are relevant nor the number $k$ of relevant features. In comparison, the regret of traditional linear bandits is $d\sqrt{T}$, where $d$ is the total number of (relevant and irrelevant) features, so the improvement can be dramatic if $k\ll d$. The computational complexity of the new algorithm is proportional to $k$ rather than $d$, making it much more suitable for real-world applications compared to traditional linear bandits. We demonstrate the performance of the new algorithm with synthetic and real human-labeled data. |
| Tasks | |
| Published | 2019-03-09 |
| URL | http://arxiv.org/abs/1903.03705v2 |
| http://arxiv.org/pdf/1903.03705v2.pdf | |
| PWC | https://paperswithcode.com/paper/linear-bandits-with-feature-feedback |
| Repo | |
| Framework | |
Efficient Automatic Meta Optimization Search for Few-Shot Learning
| Title | Efficient Automatic Meta Optimization Search for Few-Shot Learning |
| Authors | Xinyue Zheng, Peng Wang, Qigang Wang, Zhongchao shi, Feiyu Xu |
| Abstract | Previous works on meta-learning either relied on elaborately hand-designed network structures or adopted specialized learning rules to a particular domain. We propose a universal framework to optimize the meta-learning process automatically by adopting neural architecture search technique (NAS). NAS automatically generates and evaluates meta-learner’s architecture for few-shot learning problems, while the meta-learner uses meta-learning algorithm to optimize its parameters based on the distribution of learning tasks. Parameter sharing and experience replay are adopted to accelerate the architectures searching process, so it takes only 1-2 GPU days to find good architectures. Extensive experiments on Mini-ImageNet and Omniglot show that our algorithm excels in few-shot learning tasks. The best architecture found on Mini-ImageNet achieves competitive results when transferred to Omniglot, which shows the high transferability of architectures among different computer vision problems. |
| Tasks | Few-Shot Learning, Meta-Learning, Neural Architecture Search, Omniglot |
| Published | 2019-09-06 |
| URL | https://arxiv.org/abs/1909.03817v1 |
| https://arxiv.org/pdf/1909.03817v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-automatic-meta-optimization-search |
| Repo | |
| Framework | |
Predicting Patent Citations to measure Economic Impact of Scholarly Research
| Title | Predicting Patent Citations to measure Economic Impact of Scholarly Research |
| Authors | Abdul Rahman Shaikh, Hamed Alhoori |
| Abstract | A crucial goal of funding research and development has always been to advance economic development. On this basis, a consider-able body of research undertaken with the purpose of determining what exactly constitutes economic impact and how to accurately measure that impact has been published. Numerous indicators have been used to measure economic impact, although no single indicator has been widely adapted. Based on patent data collected from Altmetric we predict patent citations through various social media features using several classification models. Patents citing a research paper implies the potential it has for direct application inits field. These predictions can be utilized by researchers in deter-mining the practical applications for their work when applying for patents. |
| Tasks | |
| Published | 2019-06-07 |
| URL | https://arxiv.org/abs/1906.08244v1 |
| https://arxiv.org/pdf/1906.08244v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-patent-citations-to-measure |
| Repo | |
| Framework | |
TrendNets: Mapping Emerging Research Trends From Dynamic Co-Word Networks via Sparse Representation
| Title | TrendNets: Mapping Emerging Research Trends From Dynamic Co-Word Networks via Sparse Representation |
| Authors | Marie Katsurai, Shunsuke Ono |
| Abstract | Mapping the knowledge structure from word co-occurrences in a collection of academic papers has been widely used to provide insight into the topic evolution in an arbitrary research field. In a traditional approach, the paper collection is first divided into temporal subsets, and then a co-word network is independently depicted in a 2D map to characterize each period’s trend. To effectively map emerging research trends from such a time-series of co-word networks, this paper presents TrendNets, a novel visualization methodology that highlights the rapid changes in edge weights over time. Specifically, we formulated a new convex optimization framework that decomposes the matrix constructed from dynamic co-word networks into a smooth part and a sparse part: the former represents stationary research topics, while the latter corresponds to bursty research topics. Simulation results on synthetic data demonstrated that our matrix decomposition approach achieved the best burst detection performance over four baseline methods. In experiments conducted using papers published in the past 16 years at three conferences in different fields, we showed the effectiveness of TrendNets compared to the traditional co-word representation. We have made our codes available on the Web to encourage scientific mapping in all research fields. |
| Tasks | Time Series |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.10960v2 |
| https://arxiv.org/pdf/1905.10960v2.pdf | |
| PWC | https://paperswithcode.com/paper/trendnets-mapping-research-trends-from |
| Repo | |
| Framework | |
Adaptive Reduced Rank Regression
| Title | Adaptive Reduced Rank Regression |
| Authors | Qiong Wu, Felix Ming Fai Wong, Zhenming Liu, Yanhua Li, Varun Kanade |
| Abstract | We study the low rank regression problem $\mathbf{y} = M\mathbf{x} + \epsilon$, where $\mathbf{x}$ and $\mathbf{y}$ are $d_1$ and $d_2$ dimensional vectors respectively. We consider the extreme high-dimensional setting where the number of observations $n$ is less than $d_1 + d_2$. Existing algorithms are designed for settings where $n$ is typically as large as $\mathrm{rank}(M)(d_1+d_2)$. This work provides an efficient algorithm which only involves two SVD, and establishes statistical guarantees on its performance. The algorithm decouples the problem by first estimating the precision matrix of the features, and then solving the matrix denoising problem. To complement the upper bound, we introduce new techniques for establishing lower bounds on the performance of any algorithm for this problem. Our preliminary experiments confirm that our algorithm often out-performs existing baselines, and is always at least competitive. |
| Tasks | Denoising |
| Published | 2019-05-28 |
| URL | https://arxiv.org/abs/1905.11566v2 |
| https://arxiv.org/pdf/1905.11566v2.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-reduced-rank-regression |
| Repo | |
| Framework | |
NeuroMask: Explaining Predictions of Deep Neural Networks through Mask Learning
| Title | NeuroMask: Explaining Predictions of Deep Neural Networks through Mask Learning |
| Authors | Moustafa Alzantot, Amy Widdicombe, Simon Julier, Mani Srivastava |
| Abstract | Deep Neural Networks (DNNs) deliver state-of-the-art performance in many image recognition and understanding applications. However, despite their outstanding performance, these models are black-boxes and it is hard to understand how they make their decisions. Over the past few years, researchers have studied the problem of providing explanations of why DNNs predicted their results. However, existing techniques are either obtrusive, requiring changes in model training, or suffer from low output quality. In this paper, we present a novel method, NeuroMask, for generating an interpretable explanation of classification model results. When applied to image classification models, NeuroMask identifies the image parts that are most important to classifier results by applying a mask that hides/reveals different parts of the image, before feeding it back into the model. The mask values are tuned by minimizing a properly designed cost function that preserves the classification result and encourages producing an interpretable mask. Experiments using state-of-the-art Convolutional Neural Networks for image recognition on different datasets (CIFAR-10 and ImageNet) show that NeuroMask successfully localizes the parts of the input image which are most relevant to the DNN decision. By showing a visual quality comparison between NeuroMask explanations and those of other methods, we find NeuroMask to be both accurate and interpretable. |
| Tasks | Image Classification |
| Published | 2019-08-05 |
| URL | https://arxiv.org/abs/1908.04389v1 |
| https://arxiv.org/pdf/1908.04389v1.pdf | |
| PWC | https://paperswithcode.com/paper/neuromask-explaining-predictions-of-deep |
| Repo | |
| Framework | |
Study of Distributed Robust Beamforming with Low-Rank and Cross-Correlation Techniques
| Title | Study of Distributed Robust Beamforming with Low-Rank and Cross-Correlation Techniques |
| Authors | H. Ruan, R. C. de Lamare |
| Abstract | In this work, we present a novel robust distributed beamforming (RDB) approach based on low-rank and cross-correlation techniques. The proposed RDB approach mitigates the effects of channel errors in wireless networks equipped with relays based on the exploitation of the cross-correlation between the received data from the relays at the destination and the system output and low-rank techniques. The relay nodes are equipped with an amplify-and-forward (AF) protocol and the channel errors are modeled using an additive matrix perturbation, which results in degradation of the system performance. The proposed method, denoted low-rank and cross-correlation RDB (LRCC-RDB), considers a total relay transmit power constraint in the system and the goal of maximizing the output signal-to-interference-plus-noise ratio (SINR). We carry out a performance analysis of the proposed LRCC-RDB technique along with a computational complexity study. The proposed LRCC-RDB does not require any costly online optimization procedure and simulations show an excellent performance as compared to previously reported algorithms. |
| Tasks | |
| Published | 2019-11-27 |
| URL | https://arxiv.org/abs/1912.01506v1 |
| https://arxiv.org/pdf/1912.01506v1.pdf | |
| PWC | https://paperswithcode.com/paper/study-of-distributed-robust-beamforming-with |
| Repo | |
| Framework | |
Automatic detection of surgical site infections from a clinical data warehouse
| Title | Automatic detection of surgical site infections from a clinical data warehouse |
| Authors | Marine Quéroué, Agnès Lashéras-Bauduin, Vianney Jouhet, Frantz Thiessard, Jean-Marc Vital, Anne-Marie Rogues, Sébastien Cossin |
| Abstract | Reducing the incidence of surgical site infections (SSIs) is one of the objectives of the French nosocomial infection control program. Manual monitoring of SSIs is carried out each year by the hospital hygiene team and surgeons at the University Hospital of Bordeaux. Our goal was to develop an automatic detection algorithm based on hospital information system data. Three years (2015, 2016 and 2017) of manual spine surgery monitoring have been used as a gold standard to extract features and train machine learning algorithms. The dataset contained 22 SSIs out of 2133 spine surgeries. Two different approaches were compared. The first used several data sources and achieved the best performance but is difficult to generalize to other institutions. The second was based on free text only with semiautomatic extraction of discriminant terms. The algorithms managed to identify all the SSIs with 20 and 26 false positives respectively on the dataset. Another evaluation is underway. These results are encouraging for the development of semi-automated surveillance methods. |
| Tasks | |
| Published | 2019-09-16 |
| URL | https://arxiv.org/abs/1909.07054v1 |
| https://arxiv.org/pdf/1909.07054v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-detection-of-surgical-site |
| Repo | |
| Framework | |
Modeling user context for valence prediction from narratives
| Title | Modeling user context for valence prediction from narratives |
| Authors | Aniruddha Tammewar, Alessandra Cervone, Eva-Maria Messner, Giuseppe Riccardi |
| Abstract | Automated prediction of valence, one key feature of a person’s emotional state, from individuals’ personal narratives may provide crucial information for mental healthcare (e.g. early diagnosis of mental diseases, supervision of disease course, etc.). In the Interspeech 2018 ComParE Self-Assessed Affect challenge, the task of valence prediction was framed as a three-class classification problem using 8 seconds fragments from individuals’ narratives. As such, the task did not allow for exploring contextual information of the narratives. In this work, we investigate the intrinsic information from multiple narratives recounted by the same individual in order to predict their current state-of-mind. Furthermore, with generalizability in mind, we decided to focus our experiments exclusively on textual information as the public availability of audio narratives is limited compared to text. Our hypothesis is, that context modeling might provide insights about emotion triggering concepts (e.g. events, people, places) mentioned in the narratives that are linked to an individual’s state of mind. We explore multiple machine learning techniques to model narratives. We find that the models are able to capture inter-individual differences, leading to more accurate predictions of an individual’s emotional state, as compared to single narratives. |
| Tasks | |
| Published | 2019-05-09 |
| URL | https://arxiv.org/abs/1905.05701v2 |
| https://arxiv.org/pdf/1905.05701v2.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-user-context-for-valence-prediction |
| Repo | |
| Framework | |
Derivative-Free Global Optimization Algorithms: Population based Methods and Random Search Approaches
| Title | Derivative-Free Global Optimization Algorithms: Population based Methods and Random Search Approaches |
| Authors | Jiawei Zhang |
| Abstract | In this paper, we will provide an introduction to the derivative-free optimization algorithms which can be potentially applied to train deep learning models. Existing deep learning model training is mostly based on the back propagation algorithm, which updates the model variables layers by layers with the gradient descent algorithm or its variants. However, the objective functions of deep learning models to be optimized are usually non-convex and the gradient descent algorithms based on the first-order derivative can get stuck into the local optima very easily. To resolve such a problem, various local or global optimization algorithms have been proposed, which can help improve the training of deep learning models greatly. The representative examples include the Bayesian methods, Shubert-Piyavskii algorithm, Direct, LIPO, MCS, GA, SCE, DE, PSO, ES, CMA-ES, hill climbing and simulated annealing, etc. This is a follow-up paper of [18], and we will introduce the population based optimization algorithms, e.g., GA, SCE, DE, PSO, ES and CMA-ES, and random search algorithms, e.g., hill climbing and simulated annealing, in this paper. For the introduction to the other derivative-free optimization algorithms, please refer to [18] for more information. |
| Tasks | |
| Published | 2019-04-19 |
| URL | http://arxiv.org/abs/1904.09368v1 |
| http://arxiv.org/pdf/1904.09368v1.pdf | |
| PWC | https://paperswithcode.com/paper/190409368 |
| Repo | |
| Framework | |
Multi-scale Template Matching with Scalable Diversity Similarity in an Unconstrained Environment
| Title | Multi-scale Template Matching with Scalable Diversity Similarity in an Unconstrained Environment |
| Authors | Yi Zhang, Chao Zhang, Takuya Akashi |
| Abstract | We propose a novel multi-scale template matching method which is robust against both scaling and rotation in unconstrained environments. The key component behind is a similarity measure referred to as scalable diversity similarity (SDS). Specifically, SDS exploits bidirectional diversity of the nearest neighbor (NN) matches between two sets of points. To address the scale-robustness of the similarity measure, local appearance and rank information are jointly used for the NN search. Furthermore, by introducing penalty term on the scale change, and polar radius term into the similarity measure, SDS is shown to be a well-performing similarity measure against overall size and rotation changes, as well as non-rigid geometric deformations, background clutter, and occlusions. The properties of SDS are statistically justified, and experiments on both synthetic and real-world data show that SDS can significantly outperform state-of-the-art methods. |
| Tasks | |
| Published | 2019-07-02 |
| URL | https://arxiv.org/abs/1907.01150v1 |
| https://arxiv.org/pdf/1907.01150v1.pdf | |
| PWC | https://paperswithcode.com/paper/multi-scale-template-matching-with-scalable |
| Repo | |
| Framework | |
News Labeling as Early as Possible: Real or Fake?
| Title | News Labeling as Early as Possible: Real or Fake? |
| Authors | Maryam Ramezani, Mina Rafiei, Soroush Omranpour, Hamid R. Rabiee |
| Abstract | Making disguise between real and fake news propagation through online social networks is an important issue in many applications. The time gap between the news release time and detection of its label is a significant step towards broadcasting the real information and avoiding the fake. Therefore, one of the challenging tasks in this area is to identify fake and real news in early stages of propagation. However, there is a trade-off between minimizing the time gap and maximizing accuracy. Despite recent efforts in detection of fake news, there has been no significant work that explicitly incorporates early detection in its model. In this paper, we focus on accurate early labeling of news, and propose a model by considering earliness both in modeling and prediction. The proposed method utilizes recurrent neural networks with a novel loss function, and a new stopping rule. Given the context of news, we first embed it with a class-specific text representation. Then, we utilize the available public profile of users, and speed of news diffusion, for early labeling of the news. Experiments on real datasets demonstrate the effectiveness of our model both in terms of early labelling and accuracy, compared to the state of the art baseline and models. |
| Tasks | |
| Published | 2019-06-08 |
| URL | https://arxiv.org/abs/1906.03423v1 |
| https://arxiv.org/pdf/1906.03423v1.pdf | |
| PWC | https://paperswithcode.com/paper/news-labeling-as-early-as-possible-real-or |
| Repo | |
| Framework | |
Diversity in Faces
| Title | Diversity in Faces |
| Authors | Michele Merler, Nalini Ratha, Rogerio S. Feris, John R. Smith |
| Abstract | Face recognition is a long standing challenge in the field of Artificial Intelligence (AI). The goal is to create systems that accurately detect, recognize, verify, and understand human faces. There are significant technical hurdles in making these systems accurate, particularly in unconstrained settings due to confounding factors related to pose, resolution, illumination, occlusion, and viewpoint. However, with recent advances in neural networks, face recognition has achieved unprecedented accuracy, largely built on data-driven deep learning methods. While this is encouraging, a critical aspect that is limiting facial recognition accuracy and fairness is inherent facial diversity. Every face is different. Every face reflects something unique about us. Aspects of our heritage - including race, ethnicity, culture, geography - and our individual identify - age, gender, and other visible manifestations of self-expression, are reflected in our faces. We expect face recognition to work equally accurately for every face. Face recognition needs to be fair. As we rely on data-driven methods to create face recognition technology, we need to ensure necessary balance and coverage in training data. However, there are still scientific questions about how to represent and extract pertinent facial features and quantitatively measure facial diversity. Towards this goal, Diversity in Faces (DiF) provides a data set of one million annotated human face images for advancing the study of facial diversity. The annotations are generated using ten well-established facial coding schemes from the scientific literature. The facial coding schemes provide human-interpretable quantitative measures of facial features. We believe that by making the extracted coding schemes available on a large set of faces, we can accelerate research and development towards creating more fair and accurate facial recognition systems. |
| Tasks | Face Recognition |
| Published | 2019-01-29 |
| URL | http://arxiv.org/abs/1901.10436v6 |
| http://arxiv.org/pdf/1901.10436v6.pdf | |
| PWC | https://paperswithcode.com/paper/diversity-in-faces |
| Repo | |
| Framework | |
Adaptive Sensor Placement for Continuous Spaces
| Title | Adaptive Sensor Placement for Continuous Spaces |
| Authors | James A Grant, Alexis Boukouvalas, Ryan-Rhys Griffiths, David S Leslie, Sattar Vakili, Enrique Munoz de Cote |
| Abstract | We consider the problem of adaptively placing sensors along an interval to detect stochastically-generated events. We present a new formulation of the problem as a continuum-armed bandit problem with feedback in the form of partial observations of realisations of an inhomogeneous Poisson process. We design a solution method by combining Thompson sampling with nonparametric inference via increasingly granular Bayesian histograms and derive an $\tilde{O}(T^{2/3})$ bound on the Bayesian regret in $T$ rounds. This is coupled with the design of an efficent optimisation approach to select actions in polynomial time. In simulations we demonstrate our approach to have substantially lower and less variable regret than competitor algorithms. |
| Tasks | |
| Published | 2019-05-16 |
| URL | https://arxiv.org/abs/1905.06821v1 |
| https://arxiv.org/pdf/1905.06821v1.pdf | |
| PWC | https://paperswithcode.com/paper/adaptive-sensor-placement-for-continuous |
| Repo | |
| Framework | |
Activity Recognition and Prediction in Real Homes
| Title | Activity Recognition and Prediction in Real Homes |
| Authors | Flavia Dias Casagrande, Evi Zouganeli |
| Abstract | In this paper, we present work in progress on activity recognition and prediction in real homes using either binary sensor data or depth video data. We present our field trial and set-up for collecting and storing the data, our methods, and our current results. We compare the accuracy of predicting the next binary sensor event using probabilistic methods and Long Short-Term Memory (LSTM) networks, include the time information to improve prediction accuracy, as well as predict both the next sensor event and its mean time of occurrence using one LSTM model. We investigate transfer learning between apartments and show that it is possible to pre-train the model with data from other apartments and achieve good accuracy in a new apartment straight away. In addition, we present preliminary results from activity recognition using low-resolution depth video data from seven apartments, and classify four activities - no movement, standing up, sitting down, and TV interaction - by using a relatively simple processing method where we apply an Infinite Impulse Response (IIR) filter to extract movements from the frames prior to feeding them to a convolutional LSTM network for the classification. |
| Tasks | Activity Recognition, Transfer Learning |
| Published | 2019-05-20 |
| URL | https://arxiv.org/abs/1905.08654v1 |
| https://arxiv.org/pdf/1905.08654v1.pdf | |
| PWC | https://paperswithcode.com/paper/activity-recognition-and-prediction-in-real |
| Repo | |
| Framework | |
