Paper Group ANR 2
Graph Neural News Recommendation with Long-term and Short-term Interest Modeling. Deformable Tube Network for Action Detection in Videos. Naive Bayes with Correlation Factor for Text Classification Problem. Conformance Checking Approximation using Subset Selection and Edit Distance. Optimal Robust Learning of Discrete Distributions from Batches. Id …
Graph Neural News Recommendation with Long-term and Short-term Interest Modeling
| Title | Graph Neural News Recommendation with Long-term and Short-term Interest Modeling |
| Authors | Linmei Hu, Chen Li, Chuan Shi, Cheng Yang, Chao Shao |
| Abstract | With the information explosion of news articles, personalized news recommendation has become important for users to quickly find news that they are interested in. Existing methods on news recommendation mainly include collaborative filtering methods which rely on direct user-item interactions and content based methods which characterize the content of user reading history. Although these methods have achieved good performances, they still suffer from data sparse problem, since most of them fail to extensively exploit high-order structure information (similar users tend to read similar news articles) in news recommendation systems. In this paper, we propose to build a heterogeneous graph to explicitly model the interactions among users, news and latent topics. The incorporated topic information would help indicate a user’s interest and alleviate the sparsity of user-item interactions. Then we take advantage of graph neural networks to learn user and news representations that encode high-order structure information by propagating embeddings over the graph. The learned user embeddings with complete historic user clicks capture the users’ long-term interests. We also consider a user’s short-term interest using the recent reading history with an attention based LSTM model. Experimental results on real-world datasets show that our proposed model significantly outperforms state-of-the-art methods on news recommendation. |
| Tasks | Recommendation Systems |
| Published | 2019-10-30 |
| URL | https://arxiv.org/abs/1910.14025v2 |
| https://arxiv.org/pdf/1910.14025v2.pdf | |
| PWC | https://paperswithcode.com/paper/graph-neural-news-recommendation-with-long |
| Repo | |
| Framework | |
Deformable Tube Network for Action Detection in Videos
| Title | Deformable Tube Network for Action Detection in Videos |
| Authors | Wei Li, Zehuan Yuan, Dashan Guo, Lei Huang, Xiangzhong Fang, Changhu Wang |
| Abstract | We address the problem of spatio-temporal action detection in videos. Existing methods commonly either ignore temporal context in action recognition and localization, or lack the modelling of flexible shapes of action tubes. In this paper, we propose a two-stage action detector called Deformable Tube Network (DTN), which is composed of a Deformation Tube Proposal Network (DTPN) and a Deformable Tube Recognition Network (DTRN) similar to the Faster R-CNN architecture. In DTPN, a fast proposal linking algorithm (FTL) is introduced to connect region proposals across frames to generate multiple deformable action tube proposals. To perform action detection, we design a 3D convolution network with skip connections for tube classification and regression. Modelling action proposals as deformable tubes explicitly considers the shape of action tubes compared to 3D cuboids. Moreover, 3D convolution based recognition network can learn temporal dynamics sufficiently for action detection. Our experimental results show that we significantly outperform the methods with 3D cuboids and obtain the state-of-the-art results on both UCF-Sports and AVA datasets. |
| Tasks | Action Detection |
| Published | 2019-07-03 |
| URL | https://arxiv.org/abs/1907.01847v1 |
| https://arxiv.org/pdf/1907.01847v1.pdf | |
| PWC | https://paperswithcode.com/paper/deformable-tube-network-for-action-detection |
| Repo | |
| Framework | |
Naive Bayes with Correlation Factor for Text Classification Problem
| Title | Naive Bayes with Correlation Factor for Text Classification Problem |
| Authors | Jiangning Chen, Zhibo Dai, Juntao Duan, Heinrich Matzinger, Ionel Popescu |
| Abstract | Naive Bayes estimator is widely used in text classification problems. However, it doesn’t perform well with small-size training dataset. We propose a new method based on Naive Bayes estimator to solve this problem. A correlation factor is introduced to incorporate the correlation among different classes. Experimental results show that our estimator achieves a better accuracy compared with traditional Naive Bayes in real world data. |
| Tasks | Text Classification |
| Published | 2019-05-08 |
| URL | https://arxiv.org/abs/1905.06115v1 |
| https://arxiv.org/pdf/1905.06115v1.pdf | |
| PWC | https://paperswithcode.com/paper/190506115 |
| Repo | |
| Framework | |
Conformance Checking Approximation using Subset Selection and Edit Distance
| Title | Conformance Checking Approximation using Subset Selection and Edit Distance |
| Authors | Mohammadreza Fani Sani, Sebastiaan J. van Zelst, Wil M. P. van der Aalst |
| Abstract | Conformance checking techniques let us find out to what degree a process model and real execution data correspond to each other. In recent years, alignments have proven extremely useful in calculating conformance statistics. Most techniques to compute alignments provide an exact solution. However, in many applications, it is enough to have an approximation of the conformance value. Specifically, for large event data, the computing time for alignments is considerably long using current techniques which makes them inapplicable in reality. Also, it is no longer feasible to use standard hardware for complex processes. Hence, we need techniques that enable us to obtain fast, and at the same time, accurate approximation of the conformance values. This paper proposes new approximation techniques to compute approximated conformance checking values close to exact solution values in a faster time. Those methods also provide upper and lower bounds for the approximated alignment value. Our experiments on real event data show that it is possible to improve the performance of conformance checking by using the proposed methods compared to using the state-of-the-art alignment approximation technique. Results show that in most of the cases, we provide tight bounds, accurate approximated alignment values, and similar deviation statistics. |
| Tasks | |
| Published | 2019-12-02 |
| URL | https://arxiv.org/abs/1912.05022v1 |
| https://arxiv.org/pdf/1912.05022v1.pdf | |
| PWC | https://paperswithcode.com/paper/conformance-checking-approximation-using |
| Repo | |
| Framework | |
Optimal Robust Learning of Discrete Distributions from Batches
| Title | Optimal Robust Learning of Discrete Distributions from Batches |
| Authors | Ayush Jain, Alon Orlitsky |
| Abstract | Many applications, including natural language processing, sensor networks, collaborative filtering, and federated learning, call for estimating discrete distributions from data collected in batches, some of which may be untrustworthy, erroneous, faulty, or even adversarial. Previous estimators for this setting ran in exponential time, and for some regimes required a suboptimal number of batches. We provide the first polynomial-time estimator that is optimal in the number of batches and achieves essentially the best possible estimation accuracy. |
| Tasks | |
| Published | 2019-11-19 |
| URL | https://arxiv.org/abs/1911.08532v2 |
| https://arxiv.org/pdf/1911.08532v2.pdf | |
| PWC | https://paperswithcode.com/paper/robust-learning-of-discrete-distributions |
| Repo | |
| Framework | |
Identifying Missing Component in the Bechdel Test Using Principal Component Analysis Method
| Title | Identifying Missing Component in the Bechdel Test Using Principal Component Analysis Method |
| Authors | Raghav Lakhotia, Chandra Kanth Nagesh, Krishna Madgula |
| Abstract | A lot has been said and discussed regarding the rationale and significance of the Bechdel Score. It became a digital sensation in 2013 when Swedish cinemas began to showcase the Bechdel test score of a film alongside its rating. The test has drawn criticism from experts and the film fraternity regarding its use to rate the female presence in a movie. The pundits believe that the score is too simplified and the underlying criteria of a film to pass the test must include 1) at least two women, 2) who have at least one dialogue, 3) about something other than a man, is egregious. In this research, we have considered a few more parameters which highlight how we represent females in film, like the number of female dialogues in a movie, dialogue genre, and part of speech tags in the dialogue. The parameters were missing in the existing criteria to calculate the Bechdel score. The research aims to analyze 342 movies scripts to test a hypothesis if these extra parameters, above with the current Bechdel criteria, are significant in calculating the female representation score. The result of the Principal Component Analysis method concludes that the female dialogue content is a key component and should be considered while measuring the representation of women in a work of fiction. |
| Tasks | |
| Published | 2019-06-19 |
| URL | https://arxiv.org/abs/1907.03702v1 |
| https://arxiv.org/pdf/1907.03702v1.pdf | |
| PWC | https://paperswithcode.com/paper/identifying-missing-component-in-the-bechdel |
| Repo | |
| Framework | |
Techniques for Adversarial Examples Threatening the Safety of Artificial Intelligence Based Systems
| Title | Techniques for Adversarial Examples Threatening the Safety of Artificial Intelligence Based Systems |
| Authors | Utku Kose |
| Abstract | Artificial intelligence is known as the most effective technological field for rapid developments shaping the future of the world. Even today, it is possible to see intense use of intelligence systems in all fields of the life. Although advantages of the Artificial Intelligence are widely observed, there is also a dark side employing efforts to design hacking oriented techniques against Artificial Intelligence. Thanks to such techniques, it is possible to trick intelligent systems causing directed results for unsuccessful outputs. That is critical for also cyber wars of the future as it is predicted that the wars will be done unmanned, autonomous intelligent systems. Moving from the explanations, objective of this study is to provide information regarding adversarial examples threatening the Artificial Intelligence and focus on details of some techniques, which are used for creating adversarial examples. Adversarial examples are known as training data, which can trick a Machine Learning technique to learn incorrectly about the target problem and cause an unsuccessful or maliciously directed intelligent system at the end. The study enables the readers to learn enough about details of recent techniques for creating adversarial examples. |
| Tasks | |
| Published | 2019-09-29 |
| URL | https://arxiv.org/abs/1910.06907v1 |
| https://arxiv.org/pdf/1910.06907v1.pdf | |
| PWC | https://paperswithcode.com/paper/techniques-for-adversarial-examples |
| Repo | |
| Framework | |
Learning a Behavior Model of Hybrid Systems Through Combining Model-Based Testing and Machine Learning (Full Version)
| Title | Learning a Behavior Model of Hybrid Systems Through Combining Model-Based Testing and Machine Learning (Full Version) |
| Authors | Bernhard K. Aichernig, Roderick Bloem, Masoud Ebrahimi, Martin Horn, Franz Pernkopf, Wolfgang Roth, Astrid Rupp, Martin Tappler, Markus Tranninger |
| Abstract | Models play an essential role in the design process of cyber-physical systems. They form the basis for simulation and analysis and help in identifying design problems as early as possible. However, the construction of models that comprise physical and digital behavior is challenging. Therefore, there is considerable interest in learning such hybrid behavior by means of machine learning which requires sufficient and representative training data covering the behavior of the physical system adequately. In this work, we exploit a combination of automata learning and model-based testing to generate sufficient training data fully automatically. Experimental results on a platooning scenario show that recurrent neural networks learned with this data achieved significantly better results compared to models learned from randomly generated data. In particular, the classification error for crash detection is reduced by a factor of five and a similar F1-score is obtained with up to three orders of magnitude fewer training samples. |
| Tasks | |
| Published | 2019-07-10 |
| URL | https://arxiv.org/abs/1907.04708v1 |
| https://arxiv.org/pdf/1907.04708v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-a-behavior-model-of-hybrid-systems |
| Repo | |
| Framework | |
Supervised Quantization for Similarity Search
| Title | Supervised Quantization for Similarity Search |
| Authors | Xiaojuan Wang, Ting Zhang, Guo-Jun Q, Jinhui Tang, Jingdong Wang |
| Abstract | In this paper, we address the problem of searching for semantically similar images from a large database. We present a compact coding approach, supervised quantization. Our approach simultaneously learns feature selection that linearly transforms the database points into a low-dimensional discriminative subspace, and quantizes the data points in the transformed space. The optimization criterion is that the quantized points not only approximate the transformed points accurately, but also are semantically separable: the points belonging to a class lie in a cluster that is not overlapped with other clusters corresponding to other classes, which is formulated as a classification problem. The experiments on several standard datasets show the superiority of our approach over the state-of-the art supervised hashing and unsupervised quantization algorithms. |
| Tasks | Feature Selection, Quantization |
| Published | 2019-02-02 |
| URL | http://arxiv.org/abs/1902.00617v1 |
| http://arxiv.org/pdf/1902.00617v1.pdf | |
| PWC | https://paperswithcode.com/paper/supervised-quantization-for-similarity-search |
| Repo | |
| Framework | |
Locally Differentially Private Naive Bayes Classification
| Title | Locally Differentially Private Naive Bayes Classification |
| Authors | Emre Yilmaz, Mohammad Al-Rubaie, J. Morris Chang |
| Abstract | In machine learning, classification models need to be trained in order to predict class labels. When the training data contains personal information about individuals, collecting training data becomes difficult due to privacy concerns. Local differential privacy is a definition to measure the individual privacy when there is no trusted data curator. Individuals interact with an untrusted data aggregator who obtains statistical information about the population without learning personal data. In order to train a Naive Bayes classifier in an untrusted setting, we propose to use methods satisfying local differential privacy. Individuals send their perturbed inputs that keep the relationship between the feature values and class labels. The data aggregator estimates all probabilities needed by the Naive Bayes classifier. Then, new instances can be classified based on the estimated probabilities. We propose solutions for both discrete and continuous data. In order to eliminate high amount of noise and decrease communication cost in multi-dimensional data, we propose utilizing dimensionality reduction techniques which can be applied by individuals before perturbing their inputs. Our experimental results show that the accuracy of the Naive Bayes classifier is maintained even when the individual privacy is guaranteed under local differential privacy, and that using dimensionality reduction enhances the accuracy. |
| Tasks | Dimensionality Reduction |
| Published | 2019-05-03 |
| URL | https://arxiv.org/abs/1905.01039v1 |
| https://arxiv.org/pdf/1905.01039v1.pdf | |
| PWC | https://paperswithcode.com/paper/locally-differentially-private-naive-bayes |
| Repo | |
| Framework | |
Modeling patterns of smartphone usage and their relationship to cognitive health
| Title | Modeling patterns of smartphone usage and their relationship to cognitive health |
| Authors | Jonas Rauber, Emily B. Fox, Leon A. Gatys |
| Abstract | The ubiquity of smartphone usage in many people’s lives make it a rich source of information about a person’s mental and cognitive state. In this work we analyze 12 weeks of phone usage data from 113 older adults, 31 with diagnosed cognitive impairment and 82 without. We develop structured models of users’ smartphone interactions to reveal differences in phone usage patterns between people with and without cognitive impairment. In particular, we focus on inferring specific types of phone usage sessions that are predictive of cognitive impairment. Our model achieves an AUROC of 0.79 when discriminating between healthy and symptomatic subjects, and its interpretability enables novel insights into which aspects of phone usage strongly relate with cognitive health in our dataset. |
| Tasks | |
| Published | 2019-11-13 |
| URL | https://arxiv.org/abs/1911.05683v1 |
| https://arxiv.org/pdf/1911.05683v1.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-patterns-of-smartphone-usage-and |
| Repo | |
| Framework | |
Evolutionary Construction of Convolutional Neural Networks
| Title | Evolutionary Construction of Convolutional Neural Networks |
| Authors | Marijn van Knippenberg, Vlado Menkovski, Sergio Consoli |
| Abstract | Neuro-Evolution is a field of study that has recently gained significantly increased traction in the deep learning community. It combines deep neural networks and evolutionary algorithms to improve and/or automate the construction of neural networks. Recent Neuro-Evolution approaches have shown promising results, rivaling hand-crafted neural networks in terms of accuracy. A two-step approach is introduced where a convolutional autoencoder is created that efficiently compresses the input data in the first step, and a convolutional neural network is created to classify the compressed data in the second step. The creation of networks in both steps is guided by by an evolutionary process, where new networks are constantly being generated by mutating members of a collection of existing networks. Additionally, a method is introduced that considers the trade-off between compression and information loss of different convolutional autoencoders. This is used to select the optimal convolutional autoencoder from among those evolved to compress the data for the second step. The complete framework is implemented, tested on the popular CIFAR-10 data set, and the results are discussed. Finally, a number of possible directions for future work with this particular framework in mind are considered, including opportunities to improve its efficiency and its application in particular areas. |
| Tasks | |
| Published | 2019-01-02 |
| URL | http://arxiv.org/abs/1903.01895v1 |
| http://arxiv.org/pdf/1903.01895v1.pdf | |
| PWC | https://paperswithcode.com/paper/evolutionary-construction-of-convolutional |
| Repo | |
| Framework | |
Are you really looking at me? A Feature-Extraction Framework for Estimating Interpersonal Eye Gaze from Conventional Video
| Title | Are you really looking at me? A Feature-Extraction Framework for Estimating Interpersonal Eye Gaze from Conventional Video |
| Authors | Minh Tran, Taylan Sen, Kurtis Haut, Mohammad Rafayet Ali, Mohammed Ehsan Hoque |
| Abstract | Despite a revolution in the pervasiveness of video cameras in our daily lives, one of the most meaningful forms of nonverbal affective communication, interpersonal eye gaze, i.e. eye gaze relative to a conversation partner, is not available from common video. We introduce the Interpersonal-Calibrating Eye-gaze Encoder (ICE), which automatically extracts interpersonal gaze from video recordings without specialized hardware and without prior knowledge of participant locations. Leveraging the intuition that individuals spend a large portion of a conversation looking at each other enables the ICE dynamic clustering algorithm to extract interpersonal gaze. We validate ICE in both video chat using an objective metric with an infrared gaze tracker (F1=0.846, N=8), as well as in face-to-face communication with expert-rated evaluations of eye contact (r= 0.37, N=170). We then use ICE to analyze behavior in two different, yet important affective communication domains: interrogation-based deception detection, and communication skill assessment in speed dating. We find that honest witnesses break interpersonal gaze contact and look down more often than deceptive witnesses when answering questions (p=0.004, d=0.79). In predicting expert communication skill ratings in speed dating videos, we demonstrate that interpersonal gaze alone has more predictive power than facial expressions. |
| Tasks | Deception Detection |
| Published | 2019-06-21 |
| URL | https://arxiv.org/abs/1906.12175v2 |
| https://arxiv.org/pdf/1906.12175v2.pdf | |
| PWC | https://paperswithcode.com/paper/are-you-really-looking-at-me-a-framework-for |
| Repo | |
| Framework | |
Place Deduplication with Embeddings
| Title | Place Deduplication with Embeddings |
| Authors | Carl Yang, Do Huy Hoang, Tomas Mikolov, Jiawei Han |
| Abstract | Thanks to the advancing mobile location services, people nowadays can post about places to share visiting experience on-the-go. A large place graph not only helps users explore interesting destinations, but also provides opportunities for understanding and modeling the real world. To improve coverage and flexibility of the place graph, many platforms import places data from multiple sources, which unfortunately leads to the emergence of numerous duplicated places that severely hinder subsequent location-related services. In this work, we take the anonymous place graph from Facebook as an example to systematically study the problem of place deduplication: We carefully formulate the problem, study its connections to various related tasks that lead to several promising basic models, and arrive at a systematic two-step data-driven pipeline based on place embedding with multiple novel techniques that works significantly better than the state-of-the-art. |
| Tasks | |
| Published | 2019-09-29 |
| URL | https://arxiv.org/abs/1910.04861v1 |
| https://arxiv.org/pdf/1910.04861v1.pdf | |
| PWC | https://paperswithcode.com/paper/place-deduplication-with-embeddings |
| Repo | |
| Framework | |
Overwrite Quantization: Opportunistic Outlier Handling for Neural Network Accelerators
| Title | Overwrite Quantization: Opportunistic Outlier Handling for Neural Network Accelerators |
| Authors | Ritchie Zhao, Christopher De Sa, Zhiru Zhang |
| Abstract | Outliers in weights and activations pose a key challenge for fixed-point quantization of neural networks. While outliers can be addressed by fine-tuning, this is not practical for machine learning (ML) service providers (e.g., Google, Microsoft) who often receive customers’ models without the training data. Specialized hardware for handling outliers can enable low-precision DNNs, but incurs nontrivial area overhead. In this paper, we propose overwrite quantization (OverQ), a novel hardware technique which opportunistically increases bitwidth for outliers by letting them overwrite adjacent values. An FPGA prototype shows OverQ can significantly improve ResNet-18 accuracy at 4 bits while incurring relatively little increase in resource utilization. |
| Tasks | Quantization |
| Published | 2019-10-13 |
| URL | https://arxiv.org/abs/1910.06909v1 |
| https://arxiv.org/pdf/1910.06909v1.pdf | |
| PWC | https://paperswithcode.com/paper/overwrite-quantization-opportunistic-outlier |
| Repo | |
| Framework | |
