Paper Group ANR 1654
Fast Convolutional Dictionary Learning off the Grid. Learning review representations from user and product level information for spam detection. Machine Learning Techniques for Brand-Influencer Matchmaking on the Instagram Social Network. A critique of the DeepSec Platform for Security Analysis of Deep Learning Models. Generalized Rank Minimization …
Fast Convolutional Dictionary Learning off the Grid
| Title | Fast Convolutional Dictionary Learning off the Grid |
| Authors | Andrew H. Song, Francisco J. Flores, Demba Ba |
| Abstract | Given a continuous-time signal that can be modeled as the superposition of localized, time-shifted events from multiple sources, the goal of Convolutional Dictionary Learning (CDL) is to identify the location of the events–by Convolutional Sparse Coding (CSC)–and learn the template for each source–by Convolutional Dictionary Update (CDU). In practice, because we observe samples of the continuous-time signal on a uniformly-sampled grid in discrete time, classical CSC methods can only produce estimates of the times when the events occur on this grid, which degrades the performance of the CDU. We introduce a CDL framework that significantly reduces the errors arising from performing the estimation in discrete time. Specifically, we construct an expanded dictionary that comprises, not only discrete-time shifts of the templates, but also interpolated variants, obtained by bandlimited interpolation, that account for continuous-time shifts. For CSC, we develop a novel computationally efficient CSC algorithm, termed Convolutional Orthogonal Matching Pursuit with interpolated dictionary (COMP-INTERP). We benchmarked COMP-INTERP to Contiunuous Basis Pursuit (CBP), the state-of-the-art CSC algorithm for estimating off-the-grid events, and demonstrate, on simulated data, that 1) COMP-INTERP achieves a similar level of accuracy, and 2) is two orders of magnitude faster. For CDU, we derive a novel procedure to update the templates given sparse codes that can occur both on and off the discrete-time grid. We also show that 3) dictionary update with the overcomplete dictionary yields more accurate templates. Finally, we apply the algorithms to the spike sorting problem on electrophysiology recording and show their competitive performance. |
| Tasks | Dictionary Learning |
| Published | 2019-07-22 |
| URL | https://arxiv.org/abs/1907.09063v1 |
| https://arxiv.org/pdf/1907.09063v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-convolutional-dictionary-learning-off |
| Repo | |
| Framework | |
Learning review representations from user and product level information for spam detection
| Title | Learning review representations from user and product level information for spam detection |
| Authors | Chunyuan Yuan, Wei Zhou, Qianwen Ma, Shangwen Lv, Jizhong Han, Songlin Hu |
| Abstract | Opinion spam has become a widespread problem in social media, where hired spammers write deceptive reviews to promote or demote products to mislead the consumers for profit or fame. Existing works mainly focus on manually designing discrete textual or behavior features, which cannot capture complex semantics of reviews. Although recent works apply deep learning methods to learn review-level semantic features, their models ignore the impact of the user-level and product-level information on learning review semantics and the inherent user-review-product relationship information. In this paper, we propose a Hierarchical Fusion Attention Network (HFAN) to automatically learn the semantics of reviews from the user and product level. Specifically, we design a multi-attention unit to extract user(product)-related review information. Then, we use orthogonal decomposition and fusion attention to learn a user, review, and product representation from the review information. Finally, we take the review as a relation between user and product entity and apply TransH to jointly encode this relationship into review representation. Experimental results obtained more than 10% absolute precision improvement over the state-of-the-art performances on four real-world datasets, which show the effectiveness and versatility of the model. |
| Tasks | |
| Published | 2019-09-10 |
| URL | https://arxiv.org/abs/1909.04455v1 |
| https://arxiv.org/pdf/1909.04455v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-review-representations-from-user-and |
| Repo | |
| Framework | |
Machine Learning Techniques for Brand-Influencer Matchmaking on the Instagram Social Network
| Title | Machine Learning Techniques for Brand-Influencer Matchmaking on the Instagram Social Network |
| Authors | Taylor Sweet, Austin Rothwell, Xuan Luo |
| Abstract | The social media revolution has changed the way that brands interact with consumers. Instead of spending their advertising budget on interstate billboards, more and more companies are choosing to partner with so-called Internet “influencers” — individuals who have gained a loyal following on online platforms for the high quality of the content they post. Unfortunately, it’s not always easy for small brands to find the right influencer: someone who aligns with their corporate image and has not yet grown in popularity to the point of unaffordability. In this paper we sought to develop a system for brand-influencer matchmaking, harnessing the power and flexibility of modern machine learning techniques. The result is an algorithm that can predict the most fruitful brand-influencer partnerships based on the similarity of the content they post. |
| Tasks | |
| Published | 2019-01-17 |
| URL | http://arxiv.org/abs/1901.05949v1 |
| http://arxiv.org/pdf/1901.05949v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-techniques-for-brand |
| Repo | |
| Framework | |
A critique of the DeepSec Platform for Security Analysis of Deep Learning Models
| Title | A critique of the DeepSec Platform for Security Analysis of Deep Learning Models |
| Authors | Nicholas Carlini |
| Abstract | At IEEE S&P 2019, the paper “DeepSec: A Uniform Platform for Security Analysis of Deep Learning Model” aims to to “systematically evaluate the existing adversarial attack and defense methods.” While the paper’s goals are laudable, it fails to achieve them and presents results that are fundamentally flawed and misleading. We explain the flaws in the DeepSec work, along with how its analysis fails to meaningfully evaluate the various attacks and defenses. Specifically, DeepSec (1) evaluates each defense obliviously, using attacks crafted against undefended models; (2) evaluates attacks and defenses using incorrect implementations that greatly under-estimate their effectiveness; (3) evaluates the robustness of each defense as an average, not based on the most effective attack against that defense; (4) performs several statistical analyses incorrectly and fails to report variance; and, (5) as a result of these errors draws invalid conclusions and makes sweeping generalizations. |
| Tasks | Adversarial Attack |
| Published | 2019-05-17 |
| URL | https://arxiv.org/abs/1905.07112v1 |
| https://arxiv.org/pdf/1905.07112v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-critique-of-the-deepsec-platform-for |
| Repo | |
| Framework | |
Generalized Rank Minimization based Group Sparse Coding for Low-level Image Restoration via Dictionary Learning
| Title | Generalized Rank Minimization based Group Sparse Coding for Low-level Image Restoration via Dictionary Learning |
| Authors | Yunyi Li, Guan Gui, Xiefeng Cheng |
| Abstract | Recently, low-rank matrix recovery theory has been emerging as a significant progress for various image processing problems. Meanwhile, the group sparse coding (GSC) theory has led to great successes in image restoration with group contains low-rank property. In this paper, we introduce a novel GSC framework using generalized rank minimization for image restoration tasks via an effective adaptive dictionary learning scheme. For a more accurate approximation of the rank of group matrix, we proposed a generalized rank minimization model with a generalized and flexible weighted scheme and the generalized nonconvex nonsmooth relaxation function. Then an efficient generalized iteratively reweighted singular-value function thresholding (GIR-SFT) algorithm is proposed to handle the resulting minimization problem of GSC. Our proposed model is connected to image restoration (IR) problems via an alternating direction method of multipliers (ADMM) strategy. Extensive experiments on typical IR problems of image compressive sensing (CS) reconstruction, inpainting, deblurring and impulsive noise removal demonstrate that our proposed GSC framework can enhance the image restoration quality compared with many state-of-the-art methods. |
| Tasks | Compressive Sensing, Deblurring, Dictionary Learning, Image Restoration |
| Published | 2019-07-10 |
| URL | https://arxiv.org/abs/1907.04699v2 |
| https://arxiv.org/pdf/1907.04699v2.pdf | |
| PWC | https://paperswithcode.com/paper/generalized-rank-minimization-based-group |
| Repo | |
| Framework | |
Dictionary Learning with BLOTLESS Update
| Title | Dictionary Learning with BLOTLESS Update |
| Authors | Qi Yu, Wei Dai, Zoran Cvetkovic, Jubo Zhu |
| Abstract | Algorithms for learning a dictionary to sparsely represent a given dataset typically alternate between sparse coding and dictionary update stages. Methods for dictionary update aim to minimise expansion error by updating dictionary vectors and expansion coefficients given patterns of non-zero coefficients obtained in the sparse coding stage. We propose a block total least squares (BLOTLESS) algorithm for dictionary update. BLOTLESS updates a block of dictionary elements and the corresponding sparse coefficients simultaneously. In the error free case, three necessary conditions for exact recovery are identified. Lower bounds on the number of training data are established so that the necessary conditions hold with high probability. Numerical simulations show that the bounds approximate well the number of training data needed for exact dictionary recovery. Numerical experiments further demonstrate several benefits of dictionary learning with BLOTLESS update compared with state-of-the-art algorithms especially when the amount of training data is small. |
| Tasks | Dictionary Learning |
| Published | 2019-06-24 |
| URL | https://arxiv.org/abs/1906.10211v3 |
| https://arxiv.org/pdf/1906.10211v3.pdf | |
| PWC | https://paperswithcode.com/paper/dictionary-learning-with-blotless-update |
| Repo | |
| Framework | |
Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection
| Title | Graph Convolutional Label Noise Cleaner: Train a Plug-and-play Action Classifier for Anomaly Detection |
| Authors | Jia-Xing Zhong, Nannan Li, Weijie Kong, Shan Liu, Thomas H. Li, Ge Li |
| Abstract | Video anomaly detection under weak labels is formulated as a typical multiple-instance learning problem in previous works. In this paper, we provide a new perspective, i.e., a supervised learning task under noisy labels. In such a viewpoint, as long as cleaning away label noise, we can directly apply fully supervised action classifiers to weakly supervised anomaly detection, and take maximum advantage of these well-developed classifiers. For this purpose, we devise a graph convolutional network to correct noisy labels. Based upon feature similarity and temporal consistency, our network propagates supervisory signals from high-confidence snippets to low-confidence ones. In this manner, the network is capable of providing cleaned supervision for action classifiers. During the test phase, we only need to obtain snippet-wise predictions from the action classifier without any extra post-processing. Extensive experiments on 3 datasets at different scales with 2 types of action classifiers demonstrate the efficacy of our method. Remarkably, we obtain the frame-level AUC score of 82.12% on UCF-Crime. |
| Tasks | Anomaly Detection, Multiple Instance Learning |
| Published | 2019-03-18 |
| URL | http://arxiv.org/abs/1903.07256v1 |
| http://arxiv.org/pdf/1903.07256v1.pdf | |
| PWC | https://paperswithcode.com/paper/graph-convolutional-label-noise-cleaner-train |
| Repo | |
| Framework | |
Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classification
| Title | Learning to Learn and Predict: A Meta-Learning Approach for Multi-Label Classification |
| Authors | Jiawei Wu, Wenhan Xiong, William Yang Wang |
| Abstract | Many tasks in natural language processing can be viewed as multi-label classification problems. However, most of the existing models are trained with the standard cross-entropy loss function and use a fixed prediction policy (e.g., a threshold of 0.5) for all the labels, which completely ignores the complexity and dependencies among different labels. In this paper, we propose a meta-learning method to capture these complex label dependencies. More specifically, our method utilizes a meta-learner to jointly learn the training policies and prediction policies for different labels. The training policies are then used to train the classifier with the cross-entropy loss function, and the prediction policies are further implemented for prediction. Experimental results on fine-grained entity typing and text classification demonstrate that our proposed method can obtain more accurate multi-label classification results. |
| Tasks | Entity Typing, Meta-Learning, Multi-Label Classification, Text Classification |
| Published | 2019-09-09 |
| URL | https://arxiv.org/abs/1909.04176v1 |
| https://arxiv.org/pdf/1909.04176v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-learn-and-predict-a-meta-learning |
| Repo | |
| Framework | |
Towards Physics-informed Deep Learning for Turbulent Flow Prediction
| Title | Towards Physics-informed Deep Learning for Turbulent Flow Prediction |
| Authors | Rui Wang, Karthik Kashinath, Mustafa Mustafa, Adrian Albert, Rose Yu |
| Abstract | While deep learning has shown tremendous success in a wide range of domains, it remains a grand challenge to incorporate physical principles in a systematic manner to the design, training, and inference of such models. In this paper, we aim to predict turbulent flow by learning its highly nonlinear dynamics from spatiotemporal velocity fields of large-scale fluid flow simulations of relevance to turbulence modeling and climate modeling. We adopt a hybrid approach by marrying two well-established turbulent flow simulation techniques with deep learning. Specifically, we introduce trainable spectral filters in a coupled model of Reynolds-averaged Navier-Stokes (RANS) and Large Eddy Simulation (LES), followed by a specialized U-net for prediction. Our approach, which we call turbulent-Flow Net (TF-Net), is grounded in a principled physics model, yet offers the flexibility of learned representations. We compare our model, TF-Net, with state-of-the-art baselines and observe significant reductions in error for predictions 60 frames ahead. Most importantly, our method predicts physical fields that obey desirable physical characteristics, such as conservation of mass, whilst faithfully emulating the turbulent kinetic energy field and spectrum, which are critical for accurate prediction of turbulent flows. |
| Tasks | |
| Published | 2019-11-20 |
| URL | https://arxiv.org/abs/1911.08655v2 |
| https://arxiv.org/pdf/1911.08655v2.pdf | |
| PWC | https://paperswithcode.com/paper/towards-physics-informed-deep-learning-for-1 |
| Repo | |
| Framework | |
Integrating cross-modality hallucinated MRI with CT to aid mediastinal lung tumor segmentation
| Title | Integrating cross-modality hallucinated MRI with CT to aid mediastinal lung tumor segmentation |
| Authors | Jue Jiang, Jason Hu, Neelam Tyagi, Andreas Rimner, Sean L. Berry, Joseph O. Deasy, Harini Veeraraghavan |
| Abstract | Lung tumors, especially those located close to or surrounded by soft tissues like the mediastinum, are difficult to segment due to the low soft tissue contrast on computed tomography images. Magnetic resonance images contain superior soft-tissue contrast information that can be leveraged if both modalities were available for training. Therefore, we developed a cross-modality educed learning approach where MR information that is educed from CT is used to hallucinate MRI and improve CT segmentation. Our approach, called cross-modality educed deep learning segmentation (CMEDL) combines CT and pseudo MR produced from CT by aligning their features to obtain segmentation on CT. Features computed in the last two layers of parallelly trained CT and MR segmentation networks are aligned. We implemented this approach on U-net and dense fully convolutional networks (dense-FCN). Our networks were trained on unrelated cohorts from open-source the Cancer Imaging Archive CT images (N=377), an internal archive T2-weighted MR (N=81), and evaluated using separate validation (N=304) and testing (N=333) CT-delineated tumors. Our approach using both networks were significantly more accurate (U-net $P <0.001$; denseFCN $P <0.001$) than CT-only networks and achieved an accuracy (Dice similarity coefficient) of 0.71$\pm$0.15 (U-net), 0.74$\pm$0.12 (denseFCN) on validation and 0.72$\pm$0.14 (U-net), 0.73$\pm$0.12 (denseFCN) on the testing sets. Our novel approach demonstrated that educing cross-modality information through learned priors enhances CT segmentation performance |
| Tasks | |
| Published | 2019-09-10 |
| URL | https://arxiv.org/abs/1909.04542v1 |
| https://arxiv.org/pdf/1909.04542v1.pdf | |
| PWC | https://paperswithcode.com/paper/integrating-cross-modality-hallucinated-mri |
| Repo | |
| Framework | |
Image Captioning based on Deep Learning Methods: A Survey
| Title | Image Captioning based on Deep Learning Methods: A Survey |
| Authors | Yiyu Wang, Jungang Xu, Yingfei Sun, Ben He |
| Abstract | Image captioning is a challenging task and attracting more and more attention in the field of Artificial Intelligence, and which can be applied to efficient image retrieval, intelligent blind guidance and human-computer interaction, etc. In this paper, we present a survey on advances in image captioning based on Deep Learning methods, including Encoder-Decoder structure, improved methods in Encoder, improved methods in Decoder, and other improvements. Furthermore, we discussed future research directions. |
| Tasks | Image Captioning, Image Retrieval |
| Published | 2019-05-20 |
| URL | https://arxiv.org/abs/1905.08110v1 |
| https://arxiv.org/pdf/1905.08110v1.pdf | |
| PWC | https://paperswithcode.com/paper/image-captioning-based-on-deep-learning |
| Repo | |
| Framework | |
Midi Miner – A Python library for tonal tension and track classification
| Title | Midi Miner – A Python library for tonal tension and track classification |
| Authors | Rui Guo, Dorien Herremans, Thor Magnusson |
| Abstract | We present a Python library, called Midi Miner, that can calculate tonal tension and classify different tracks. MIDI (Music Instrument Digital Interface) is a hardware and software standard for communicating musical events between digital music devices. It is often used for tasks such as music representation, communication between devices, and even music generation [5]. Tension is an essential element of the music listening experience, which can come from a number of musical features including timbre, loudness and harmony [3]. Midi Miner provides a Python implementation for the tonal tension model based on the spiral array [1] as presented by Herremans and Chew [4]. Midi Miner also performs key estimation and includes a track classifier that can disentangle melody, bass, and harmony tracks. Even though tracks are often separated in MIDI files, the musical function of each track is not always clear. The track classifier keeps the identified tracks and discards messy tracks, which can enable further analysis and training tasks. |
| Tasks | Music Generation |
| Published | 2019-10-03 |
| URL | https://arxiv.org/abs/1910.02049v1 |
| https://arxiv.org/pdf/1910.02049v1.pdf | |
| PWC | https://paperswithcode.com/paper/midi-miner-a-python-library-for-tonal-tension |
| Repo | |
| Framework | |
Using Deep Neural Network for Android Malware Detection
| Title | Using Deep Neural Network for Android Malware Detection |
| Authors | Abdelmonim Naway, Yuancheng LI |
| Abstract | The pervasiveness of the Android operating system, with the availability of applications almost for everything, is readily accessible in the official Google play store or a dozen alternative third-party markets. Additionally, the vital role of smartphones in modern life leads to store significant information on devices, not only personal information but also corporate information, which attract malware developers to develop applications that can infiltrate user’s devices to steal information and perform harmful tasks. This accompanied with the limitation of currently defenses techniques such as ineffective screening in Google play store, weak or no screening in third-party markets. Antiviruses software that still relies on a signature-based database that is effective only in identifying known malware. To contrive with malicious applications that are increased in volume and sophistication, we propose an Android malware detection system that applies deep learning technique to face the threats of Android malware. Extensive experiments on a real-world dataset contain benign and malicious applications uncovered that the proposed system reaches an accuracy of 95.31%. |
| Tasks | Android Malware Detection, Malware Detection |
| Published | 2019-01-16 |
| URL | http://arxiv.org/abs/1904.00736v1 |
| http://arxiv.org/pdf/1904.00736v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-deep-neural-network-for-android-malware |
| Repo | |
| Framework | |
Modeling Winner-Take-All Competition in Sparse Binary Projections
| Title | Modeling Winner-Take-All Competition in Sparse Binary Projections |
| Authors | Wenye Li |
| Abstract | Inspired by the advances in biological science, the study of sparse binary projection models has attracted considerable recent research attention. The models project dense input samples into a higher-dimensional space and output sparse binary data representations after the Winner-Take-All competition, subject to the constraint that the projection matrix is also sparse and binary. Following the work along this line, we developed a supervised-WTA model when training samples with both input and output representations are available, from which the optimal projection matrix can be obtained with a simple, effective yet efficient algorithm. We further extended the model and the algorithm to an unsupervised setting where only the input representation of the samples is available. In a series of empirical evaluation on similarity search tasks, the proposed models reported significantly improved results over the state-of-the-art methods in both search accuracies and running speed. The successful results give us strong confidence that the work provides a highly practical tool to real world applications. |
| Tasks | |
| Published | 2019-07-27 |
| URL | https://arxiv.org/abs/1907.11959v2 |
| https://arxiv.org/pdf/1907.11959v2.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-winner-take-all-competition-in |
| Repo | |
| Framework | |
Commonsense Knowledge Mining from Pretrained Models
| Title | Commonsense Knowledge Mining from Pretrained Models |
| Authors | Joshua Feldman, Joe Davison, Alexander M. Rush |
| Abstract | Inferring commonsense knowledge is a key challenge in natural language processing, but due to the sparsity of training data, previous work has shown that supervised methods for commonsense knowledge mining underperform when evaluated on novel data. In this work, we develop a method for generating commonsense knowledge using a large, pre-trained bidirectional language model. By transforming relational triples into masked sentences, we can use this model to rank a triple’s validity by the estimated pointwise mutual information between the two entities. Since we do not update the weights of the bidirectional model, our approach is not biased by the coverage of any one commonsense knowledge base. Though this method performs worse on a test set than models explicitly trained on a corresponding training set, it outperforms these methods when mining commonsense knowledge from new sources, suggesting that unsupervised techniques may generalize better than current supervised approaches. |
| Tasks | Language Modelling |
| Published | 2019-09-02 |
| URL | https://arxiv.org/abs/1909.00505v1 |
| https://arxiv.org/pdf/1909.00505v1.pdf | |
| PWC | https://paperswithcode.com/paper/commonsense-knowledge-mining-from-pretrained |
| Repo | |
| Framework | |
