Paper Group ANR 117
Gradient Flow Algorithms for Density Propagation in Stochastic Systems. Neural-network based general method for statistical mechanics on sparse systems. Is AI different for SE?. Coverage-based Outlier Explanation. Dynamically Visual Disambiguation of Keyword-based Image Search. A Simulation Model for Pedestrian Crowd Evacuation Based on Various AI …
Gradient Flow Algorithms for Density Propagation in Stochastic Systems
| Title | Gradient Flow Algorithms for Density Propagation in Stochastic Systems |
| Authors | Kenneth F. Caluya, Abhishek Halder |
| Abstract | We develop a new computational framework to solve the partial differential equations (PDEs) governing the flow of the joint probability density functions (PDFs) in continuous-time stochastic nonlinear systems. The need for computing the transient joint PDFs subject to prior dynamics arises in uncertainty propagation, nonlinear filtering and stochastic control. Our methodology breaks away from the traditional approach of spatial discretization or function approximation – both of which, in general, suffer from the “curse-of-dimensionality”. In the proposed framework, we discretize time but not the state space. We solve infinite dimensional proximal recursions in the manifold of joint PDFs, which in the small time-step limit, is theoretically equivalent to solving the underlying transport PDEs. The resulting computation has the geometric interpretation of gradient flow of certain free energy functional with respect to the Wasserstein metric arising from the theory of optimal mass transport. We show that dualization along with an entropic regularization, leads to a cone-preserving fixed point recursion that is proved to be contractive in Thompson metric. A block co-ordinate iteration scheme is proposed to solve the resulting nonlinear recursions with guaranteed convergence. This approach enables remarkably fast computation for non-parametric transient joint PDF propagation. Numerical examples and various extensions are provided to illustrate the scope and efficacy of the proposed approach. |
| Tasks | |
| Published | 2019-08-01 |
| URL | https://arxiv.org/abs/1908.00533v2 |
| https://arxiv.org/pdf/1908.00533v2.pdf | |
| PWC | https://paperswithcode.com/paper/gradient-flow-algorithms-for-density |
| Repo | |
| Framework | |
Neural-network based general method for statistical mechanics on sparse systems
| Title | Neural-network based general method for statistical mechanics on sparse systems |
| Authors | Feng Pan, Hai-Jun Zhou, Pan Zhang |
| Abstract | We propose a general method for solving statistical mechanics problems defined on sparse graphs, such as random graphs, real-world networks, and low-dimensional lattices. Our approach extract a small feedback vertex set of the sparse graph, converting the sparse system to a strongly correlated system with many-body and dense interactions on the feedback set, then solve it using variational method based on neural networks to estimate free energy, observables, and generate unbiased samples via direct sampling. Extensive experiments show that our approach is more accurate than existing approaches for sparse spin glass systems. On random graphs and real-world networks, our approach significantly outperforms the standard methods for sparse systems such as belief-propagation; on structured sparse systems such as two-dimensional lattices our approach is significantly faster and more accurate than recently proposed variational autoregressive networks using convolution neural networks. |
| Tasks | |
| Published | 2019-06-26 |
| URL | https://arxiv.org/abs/1906.10935v1 |
| https://arxiv.org/pdf/1906.10935v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-network-based-general-method-for |
| Repo | |
| Framework | |
Is AI different for SE?
| Title | Is AI different for SE? |
| Authors | Amritanshu Agrawal, Tim Menzies |
| Abstract | What AI tools are needed for SE? Ideally, we should have simple rules that peek at data, then say “use this tool” or “use that tool”. To find such a rule, we explored 120 different data sets addressing numerous problems, including bad smell detection, predicting Github issue close time, bug report analysis, defect prediction and dozens of other non-SE problems. To this data, we apply a SE-based tool that (a)~out-performs the state-of-the-art for these SE problems yet (b)~fails very badly on standard AI problems. In those results, we can find a simple rule for when to use/avoid the SE-based tool. SE data is often about infrequent issues, like the occasional defect, or the rarely exploited security violation, or the requirement that holds for one special case. But as we show, standard AI tools work best when the target is relatively more frequent. Also, we can exploit these special properties of SE, to great effect (to rapidly find better optimizations for SE tasks via a tactic called “dodging”, explained in this paper). More generally, this result says we need a new kind of SE research for developing new AI tools that are more suited to SE problems. |
| Tasks | |
| Published | 2019-12-09 |
| URL | https://arxiv.org/abs/1912.04061v1 |
| https://arxiv.org/pdf/1912.04061v1.pdf | |
| PWC | https://paperswithcode.com/paper/is-ai-different-for-se |
| Repo | |
| Framework | |
Coverage-based Outlier Explanation
| Title | Coverage-based Outlier Explanation |
| Authors | Yue Wu, Leman Akoglu, Ian Davidson |
| Abstract | Outlier detection is a core task in data mining with a plethora of algorithms that have enjoyed wide scale usage. Existing algorithms are primarily focused on detection, that is the identification of outliers in a given dataset. In this paper we explore the relatively under-studied problem of the outlier explanation problem. Our goal is, given a dataset that is already divided into outliers and normal instances, explain what characterizes the outliers. We explore the novel direction of a semantic explanation that a domain expert or policy maker is able to understand. We formulate this as an optimization problem to find explanations that are both interpretable and pure. Through experiments on real-world data sets, we quantitatively show that our method can efficiently generate better explanations compared with rule-based learners. |
| Tasks | Outlier Detection |
| Published | 2019-11-06 |
| URL | https://arxiv.org/abs/1911.02617v1 |
| https://arxiv.org/pdf/1911.02617v1.pdf | |
| PWC | https://paperswithcode.com/paper/coverage-based-outlier-explanation |
| Repo | |
| Framework | |
Dynamically Visual Disambiguation of Keyword-based Image Search
| Title | Dynamically Visual Disambiguation of Keyword-based Image Search |
| Authors | Yazhou Yao, Zeren Sun, Fumin Shen, Li Liu, Limin Wang, Fan Zhu, Lizhong Ding, Gangshan Wu, Ling Shao |
| Abstract | Due to the high cost of manual annotation, learning directly from the web has attracted broad attention. One issue that limits their performance is the problem of visual polysemy. To address this issue, we present an adaptive multi-model framework that resolves polysemy by visual disambiguation. Compared to existing methods, the primary advantage of our approach lies in that our approach can adapt to the dynamic changes in the search results. Our proposed framework consists of two major steps: we first discover and dynamically select the text queries according to the image search results, then we employ the proposed saliency-guided deep multi-instance learning network to remove outliers and learn classification models for visual disambiguation. Extensive experiments demonstrate the superiority of our proposed approach. |
| Tasks | Image Retrieval |
| Published | 2019-05-27 |
| URL | https://arxiv.org/abs/1905.10955v1 |
| https://arxiv.org/pdf/1905.10955v1.pdf | |
| PWC | https://paperswithcode.com/paper/dynamically-visual-disambiguation-of-keyword |
| Repo | |
| Framework | |
A Simulation Model for Pedestrian Crowd Evacuation Based on Various AI Techniques
| Title | A Simulation Model for Pedestrian Crowd Evacuation Based on Various AI Techniques |
| Authors | Danial A. Muhammed, Soran A. M. Saeed, Tarik A. Rashid |
| Abstract | This paper attempts to design an intelligent simulation model for pedestrian crowd evacuation. For this purpose, the cellular automata(CA) was fully integrated with fuzzy logic, the kth nearest neighbors (KNN), and some statistical equations. In this model, each pedestrian was assigned a specific speed, according to his/her physical, biological and emotional features. The emergency behavior and evacuation efficiency of each pedestrian were evaluated by coupling his or her speed with various elements, such as environment, pedestrian distribution and familiarity with the exits. These elements all have great impacts on the evacuation process. Several experiments were carried out to verify the performance of the model in different emergency scenarios. The results show that the proposed model can predict the evacuation time and emergency behavior in various types of building interiors and pedestrian distributions. The research provides a good reference to the design of building evacuation systems. |
| Tasks | |
| Published | 2019-12-03 |
| URL | https://arxiv.org/abs/1912.01629v1 |
| https://arxiv.org/pdf/1912.01629v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-simulation-model-for-pedestrian-crowd |
| Repo | |
| Framework | |
Discovering Protagonist of Sentiment with Aspect Reconstructed Capsule Network
| Title | Discovering Protagonist of Sentiment with Aspect Reconstructed Capsule Network |
| Authors | Chi Xu, Hao Feng, Guoxin Yu, Min Yang, Xiting Wang, Xiang Ao |
| Abstract | Most recent existing aspect-term level sentiment analysis (ATSA) approaches combined various neural network models with delicately carved attention mechanisms built upon given aspect and context to generate refined sentence representations for better predictions. In these methods, aspect terms are always provided in both training and testing process which may degrade aspect-level analysis into sentence-level prediction. However, the annotated aspect term might be unavailable in real-world scenarios which may challenge the applicability of the existing methods. In this paper, we aim to improve ATSA by discovering the potential aspect terms of the predicted sentiment polarity when the aspect terms of a test sentence are unknown. We access this goal by proposing a capsule network based model named CAPSAR. In CAPSAR, sentiment categories are denoted by capsules and aspect term information is injected into sentiment capsules through a sentiment-aspect reconstruction procedure during the training. As a result, coherent patterns between aspects and sentimental expressions are encapsulated by these sentiment capsules. Experiments on three widely used benchmarks demonstrate these patterns have potential in exploring aspect terms from test sentence when only feeding the sentence to the model. Meanwhile, the proposed CAPSAR can clearly outperform SOTA methods in standard ATSA tasks. |
| Tasks | Sentiment Analysis |
| Published | 2019-12-23 |
| URL | https://arxiv.org/abs/1912.10785v2 |
| https://arxiv.org/pdf/1912.10785v2.pdf | |
| PWC | https://paperswithcode.com/paper/hunt-protagonist-of-sentiment-sentiment |
| Repo | |
| Framework | |
Automatic Reminiscence Therapy for Dementia
| Title | Automatic Reminiscence Therapy for Dementia |
| Authors | Mariona Caros, Maite Garolera, Petia Radeva, Xavier Giro-i-Nieto |
| Abstract | With people living longer than ever, the number of cases with dementia such as Alzheimer’s disease increases steadily. It affects more than 46 million people worldwide, and it is estimated that in 2050 more than 100 million will be affected. While there are not effective treatments for these terminal diseases, therapies such as reminiscence, that stimulate memories from the past are recommended. Currently, reminiscence therapy takes place in care homes and is guided by a therapist or a carer. In this work, we present an AI-based solution to automatize the reminiscence therapy, which consists in a dialogue system that uses photos as input to generate questions. We run a usability case study with patients diagnosed of mild cognitive impairment that shows they found the system very entertaining and challenging. Overall, this paper presents how reminiscence therapy can be automatized by using machine learning, and deployed to smartphones and laptops, making the therapy more accessible to every person affected by dementia. |
| Tasks | |
| Published | 2019-10-25 |
| URL | https://arxiv.org/abs/1910.11949v1 |
| https://arxiv.org/pdf/1910.11949v1.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-reminiscence-therapy-for-dementia |
| Repo | |
| Framework | |
Trojan Attacks on Wireless Signal Classification with Adversarial Machine Learning
| Title | Trojan Attacks on Wireless Signal Classification with Adversarial Machine Learning |
| Authors | Kemal Davaslioglu, Yalin E. Sagduyu |
| Abstract | We present a Trojan (backdoor or trapdoor) attack that targets deep learning applications in wireless communications. A deep learning classifier is considered to classify wireless signals using raw (I/Q) samples as features and modulation types as labels. An adversary slightly manipulates training data by inserting Trojans (i.e., triggers) to only few training data samples by modifying their phases and changing the labels of these samples to a target label. This poisoned training data is used to train the deep learning classifier. In test (inference) time, an adversary transmits signals with the same phase shift that was added as a trigger during training. While the receiver can accurately classify clean (unpoisoned) signals without triggers, it cannot reliably classify signals poisoned with triggers. This stealth attack remains hidden until activated by poisoned inputs (Trojans) to bypass a signal classifier (e.g., for authentication). We show that this attack is successful over different channel conditions and cannot be mitigated by simply preprocessing the training and test data with random phase variations. To detect this attack, activation based outlier detection is considered with statistical as well as clustering techniques. We show that the latter one can detect Trojan attacks even if few samples are poisoned. |
| Tasks | Outlier Detection |
| Published | 2019-10-23 |
| URL | https://arxiv.org/abs/1910.10766v1 |
| https://arxiv.org/pdf/1910.10766v1.pdf | |
| PWC | https://paperswithcode.com/paper/trojan-attacks-on-wireless-signal |
| Repo | |
| Framework | |
Failure Modes in Machine Learning Systems
| Title | Failure Modes in Machine Learning Systems |
| Authors | Ram Shankar Siva Kumar, David O Brien, Kendra Albert, Salomé Viljöen, Jeffrey Snover |
| Abstract | In the last two years, more than 200 papers have been written on how machine learning (ML) systems can fail because of adversarial attacks on the algorithms and data; this number balloons if we were to incorporate papers covering non-adversarial failure modes. The spate of papers has made it difficult for ML practitioners, let alone engineers, lawyers, and policymakers, to keep up with the attacks against and defenses of ML systems. However, as these systems become more pervasive, the need to understand how they fail, whether by the hand of an adversary or due to the inherent design of a system, will only become more pressing. In order to equip software developers, security incident responders, lawyers, and policy makers with a common vernacular to talk about this problem, we developed a framework to classify failures into “Intentional failures” where the failure is caused by an active adversary attempting to subvert the system to attain her goals; and “Unintentional failures” where the failure is because an ML system produces an inherently unsafe outcome. After developing the initial version of the taxonomy last year, we worked with security and ML teams across Microsoft, 23 external partners, standards organization, and governments to understand how stakeholders would use our framework. Throughout the paper, we attempt to highlight how machine learning failure modes are meaningfully different from traditional software failures from a technology and policy perspective. |
| Tasks | |
| Published | 2019-11-25 |
| URL | https://arxiv.org/abs/1911.11034v1 |
| https://arxiv.org/pdf/1911.11034v1.pdf | |
| PWC | https://paperswithcode.com/paper/failure-modes-in-machine-learning-systems |
| Repo | |
| Framework | |
Distributed generation of privacy preserving data with user customization
| Title | Distributed generation of privacy preserving data with user customization |
| Authors | Xiao Chen, Thomas Navidi, Stefano Ermon, Ram Rajagopal |
| Abstract | Distributed devices such as mobile phones can produce and store large amounts of data that can enhance machine learning models; however, this data may contain private information specific to the data owner that prevents the release of the data. We wish to reduce the correlation between user-specific private information and data while maintaining the useful information. Rather than learning a large model to achieve privatization from end to end, we introduce a decoupling of the creation of a latent representation and the privatization of data that allows user-specific privatization to occur in a distributed setting with limited computation and minimal disturbance on the utility of the data. We leverage a Variational Autoencoder (VAE) to create a compact latent representation of the data; however, the VAE remains fixed for all devices and all possible private labels. We then train a small generative filter to perturb the latent representation based on individual preferences regarding the private and utility information. The small filter is trained by utilizing a GAN-type robust optimization that can take place on a distributed device. We conduct experiments on three popular datasets: MNIST, UCI-Adult, and CelebA, and give a thorough evaluation including visualizing the geometry of the latent embeddings and estimating the empirical mutual information to show the effectiveness of our approach. |
| Tasks | |
| Published | 2019-04-20 |
| URL | http://arxiv.org/abs/1904.09415v1 |
| http://arxiv.org/pdf/1904.09415v1.pdf | |
| PWC | https://paperswithcode.com/paper/distributed-generation-of-privacy-preserving |
| Repo | |
| Framework | |
Unsupervised Transfer Learning via BERT Neuron Selection
| Title | Unsupervised Transfer Learning via BERT Neuron Selection |
| Authors | Mehrdad Valipour, En-Shiun Annie Lee, Jaime R. Jamacaro, Carolina Bessega |
| Abstract | Recent advancements in language representation models such as BERT have led to a rapid improvement in numerous natural language processing tasks. However, language models usually consist of a few hundred million trainable parameters with embedding space distributed across multiple layers, thus making them challenging to be fine-tuned for a specific task or to be transferred to a new domain. To determine whether there are task-specific neurons that can be exploited for unsupervised transfer learning, we introduce a method for selecting the most important neurons to solve a specific classification task. This algorithm is further extended to multi-source transfer learning by computing the importance of neurons for several single-source transfer learning scenarios between different subsets of data sources. Besides, a task-specific fingerprint for each data source is obtained based on the percentage of the selected neurons in each layer. We perform extensive experiments in unsupervised transfer learning for sentiment analysis, natural language inference and sentence similarity, and compare our results with the existing literature and baselines. Significantly, we found that the source and target data sources with higher degrees of similarity between their task-specific fingerprints demonstrate a better transferability property. We conclude that our method can lead to better performance using just a few hundred task-specific and interpretable neurons. |
| Tasks | Natural Language Inference, Sentiment Analysis, Transfer Learning |
| Published | 2019-12-10 |
| URL | https://arxiv.org/abs/1912.05308v1 |
| https://arxiv.org/pdf/1912.05308v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-transfer-learning-via-bert |
| Repo | |
| Framework | |
Kernel transfer over multiple views for missing data completion
| Title | Kernel transfer over multiple views for missing data completion |
| Authors | Riikka Huusari, Cécile Capponi, Paul Villoutreix, Hachem Kadri |
| Abstract | We consider the kernel completion problem with the presence of multiple views in the data. In this context the data samples can be fully missing in some views, creating missing columns and rows to the kernel matrices that are calculated individually for each view. We propose to solve the problem of completing the kernel matrices by transferring the features of the other views to represent the view under consideration. We align the known part of the kernel matrix with a new kernel built from the features of the other views. We are thus able to find generalizable structures in the kernel under completion, and represent it accurately. Its missing values can be predicted with the data available in other views. We illustrate the benefits of our approach with simulated data and multivariate digits dataset, as well as with real biological datasets from studies of pattern formation in early \textit{Drosophila melanogaster} embryogenesis. |
| Tasks | |
| Published | 2019-10-14 |
| URL | https://arxiv.org/abs/1910.05964v1 |
| https://arxiv.org/pdf/1910.05964v1.pdf | |
| PWC | https://paperswithcode.com/paper/kernel-transfer-over-multiple-views-for |
| Repo | |
| Framework | |
Context Oriented Software Middleware
| Title | Context Oriented Software Middleware |
| Authors | Basel Magableh |
| Abstract | Our middleware approach, Context-Oriented Software Middleware (COSM), supports context-dependent software with self-adaptability and dependability in a mobile computing environment. The COSM-middleware is a generic and platform-independent adaptation engine, which performs a runtime composition of the software’s context-dependent behaviours based on the execution contexts. Our middleware distinguishes between the context-dependent and context-independent functionality of software systems. This enables the COSM-middleware to adapt the application behaviour by composing a set of context-oriented components, that implement the context-dependent functionality of the software. Accordingly, the software dependability is achieved by considering the functionality of the COSM-middleware and the adaptation impact/costs. The COSM-middleware uses a dynamic policy-based engine to evaluate the adaptation outputs and verify the fitness of the adaptation output with the application’s objectives, goals and the architecture quality attributes. These capabilities are demonstrated through an empirical evaluation of a case study implementation. |
| Tasks | |
| Published | 2019-01-13 |
| URL | http://arxiv.org/abs/1901.04016v1 |
| http://arxiv.org/pdf/1901.04016v1.pdf | |
| PWC | https://paperswithcode.com/paper/context-oriented-software-middleware |
| Repo | |
| Framework | |
Stable Electromyographic Sequence Prediction During Movement Transitions using Temporal Convolutional Networks
| Title | Stable Electromyographic Sequence Prediction During Movement Transitions using Temporal Convolutional Networks |
| Authors | Joseph L. Betthauser, John T. Krall, Rahul R. Kaliki, Matthew S. Fifer, Nitish V. Thakor |
| Abstract | Transient muscle movements influence the temporal structure of myoelectric signal patterns, often leading to unstable prediction behavior from movement-pattern classification methods. We show that temporal convolutional network sequential models leverage the myoelectric signal’s history to discover contextual temporal features that aid in correctly predicting movement intentions, especially during interclass transitions. We demonstrate myoelectric classification using temporal convolutional networks to effect 3 simultaneous hand and wrist degrees-of-freedom in an experiment involving nine human-subjects. Temporal convolutional networks yield significant $(p<0.001)$ performance improvements over other state-of-the-art methods in terms of both classification accuracy and stability. |
| Tasks | |
| Published | 2019-01-08 |
| URL | http://arxiv.org/abs/1901.02442v1 |
| http://arxiv.org/pdf/1901.02442v1.pdf | |
| PWC | https://paperswithcode.com/paper/stable-electromyographic-sequence-prediction |
| Repo | |
| Framework | |
