Paper Group ANR 304
Geodesic Learning via Unsupervised Decision Forests. Fine-grained Qualitative Spatial Reasoning about Point Positions. Synthetic Defocus and Look-Ahead Autofocus for Casual Videography. ANTIQUE: A Non-Factoid Question Answering Benchmark. Feature-driven Improvement of Renewable Energy Forecasting and Trading. Robust Opponent Modeling via Adversaria …
Geodesic Learning via Unsupervised Decision Forests
| Title | Geodesic Learning via Unsupervised Decision Forests |
| Authors | Meghana Madhyastha, Percy Li, James Browne, Veronika Strnadova-Neeley, Carey E. Priebe, Randal Burns, Joshua T. Vogelstein |
| Abstract | Geodesic distance is the shortest path between two points in a Riemannian manifold. Manifold learning algorithms, such as Isomap, seek to learn a manifold that preserves geodesic distances. However, such methods operate on the ambient dimensionality, and are therefore fragile to noise dimensions. We developed an unsupervised random forest method (URerF) to approximately learn geodesic distances in linear and nonlinear manifolds with noise. URerF operates on low-dimensional sparse linear combinations of features, rather than the full observed dimensionality. To choose the optimal split in a computationally efficient fashion, we developed a fast Bayesian Information Criterion statistic for Gaussian mixture models. We introduce geodesic precision-recall curves which quantify performance relative to the true latent manifold. Empirical results on simulated and real data demonstrate that URerF is robust to high-dimensional noise, where as other methods, such as Isomap, UMAP, and FLANN, quickly deteriorate in such settings. In particular, URerF is able to estimate geodesic distances on a real connectome dataset better than other approaches. |
| Tasks | |
| Published | 2019-07-05 |
| URL | https://arxiv.org/abs/1907.02844v1 |
| https://arxiv.org/pdf/1907.02844v1.pdf | |
| PWC | https://paperswithcode.com/paper/geodesic-learning-via-unsupervised-decision |
| Repo | |
| Framework | |
Fine-grained Qualitative Spatial Reasoning about Point Positions
| Title | Fine-grained Qualitative Spatial Reasoning about Point Positions |
| Authors | Sören Schwertfeger |
| Abstract | The ability to persist in the spacial environment is, not only in the robotic context, an essential feature. Positional knowledge is one of the most important aspects of space and a number of methods to represent these information have been developed in the in the research area of spatial cognition. The basic qualitative spatial representation and reasoning techniques are presented in this thesis and several calculi are briefly reviewed. Features and applications of qualitative calculi are summarized. A new calculus for representing and reasoning about qualitative spatial orientation and distances is being designed. It supports an arbitrary level of granularity over ternary relations of points. Ways of improving the complexity of the composition are shown and an implementation of the calculus demonstrates its capabilities. Existing qualitative spatial calculi of positional information are compared to the new approach and possibilities for future research are outlined. |
| Tasks | |
| Published | 2019-11-15 |
| URL | https://arxiv.org/abs/1911.06543v1 |
| https://arxiv.org/pdf/1911.06543v1.pdf | |
| PWC | https://paperswithcode.com/paper/fine-grained-qualitative-spatial-reasoning |
| Repo | |
| Framework | |
Synthetic Defocus and Look-Ahead Autofocus for Casual Videography
| Title | Synthetic Defocus and Look-Ahead Autofocus for Casual Videography |
| Authors | Xuaner Zhang, Kevin Matzen, Vivien Nguyen, Dillon Yao, You Zhang, Ren Ng |
| Abstract | In cinema, large camera lenses create beautiful shallow depth of field (DOF), but make focusing difficult and expensive. Accurate cinema focus usually relies on a script and a person to control focus in realtime. Casual videographers often crave cinematic focus, but fail to achieve it. We either sacrifice shallow DOF, as in smartphone videos; or we struggle to deliver accurate focus, as in videos from larger cameras. This paper is about a new approach in the pursuit of cinematic focus for casual videography. We present a system that synthetically renders refocusable video from a deep DOF video shot with a smartphone, and analyzes future video frames to deliver context-aware autofocus for the current frame. To create refocusable video, we extend recent machine learning methods designed for still photography, contributing a new dataset for machine training, a rendering model better suited to cinema focus, and a filtering solution for temporal coherence. To choose focus accurately for each frame, we demonstrate autofocus that looks at upcoming video frames and applies AI-assist modules such as motion, face, audio and saliency detection. We also show that autofocus benefits from machine learning and a large-scale video dataset with focus annotation, where we use our RVR-LAAF GUI to create this sizable dataset efficiently. We deliver, for example, a shallow DOF video where the autofocus transitions onto each person before she begins to speak. This is impossible for conventional camera autofocus because it would require seeing into the future. |
| Tasks | Saliency Detection |
| Published | 2019-05-15 |
| URL | https://arxiv.org/abs/1905.06326v3 |
| https://arxiv.org/pdf/1905.06326v3.pdf | |
| PWC | https://paperswithcode.com/paper/synthetic-defocus-and-look-ahead-autofocus |
| Repo | |
| Framework | |
ANTIQUE: A Non-Factoid Question Answering Benchmark
| Title | ANTIQUE: A Non-Factoid Question Answering Benchmark |
| Authors | Helia Hashemi, Mohammad Aliannejadi, Hamed Zamani, W. Bruce Croft |
| Abstract | Considering the widespread use of mobile and voice search, answer passage retrieval for non-factoid questions plays a critical role in modern information retrieval systems. Despite the importance of the task, the community still feels the significant lack of large-scale non-factoid question answering collections with real questions and comprehensive relevance judgments. In this paper, we develop and release a collection of 2,626 open-domain non-factoid questions from a diverse set of categories. The dataset, called ANTIQUE, contains 34,011 manual relevance annotations. The questions were asked by real users in a community question answering service, i.e., Yahoo! Answers. Relevance judgments for all the answers to each question were collected through crowdsourcing. To facilitate further research, we also include a brief analysis of the data as well as baseline results on both classical and recently developed neural IR models. |
| Tasks | Community Question Answering, Information Retrieval, Question Answering |
| Published | 2019-05-22 |
| URL | https://arxiv.org/abs/1905.08957v2 |
| https://arxiv.org/pdf/1905.08957v2.pdf | |
| PWC | https://paperswithcode.com/paper/antique-a-non-factoid-question-answering |
| Repo | |
| Framework | |
Feature-driven Improvement of Renewable Energy Forecasting and Trading
| Title | Feature-driven Improvement of Renewable Energy Forecasting and Trading |
| Authors | Miguel Á. Muñoz, Juan M. Morales, Salvador Pineda |
| Abstract | Inspired from recent insights into the common ground of machine learning, optimization and decision-making, this paper proposes an easy-to-implement, but effective procedure to enhance both the quality of renewable energy forecasts and the competitive edge of renewable energy producers in electricity markets with a dual-price settlement of imbalances. The quality and economic gains brought by the proposed procedure essentially stem from the utilization of valuable predictors (also known as features) in a data-driven newsvendor model that renders a computationally inexpensive linear program. We illustrate the proposed procedure and numerically assess its benefits on a realistic case study that considers the aggregate wind power production in the Danish DK1 bidding zone as the variable to be predicted and traded. Within this context, our procedure leverages, among others, spatial information in the form of wind power forecasts issued by transmission system operators (TSO) in surrounding bidding zones and publicly available in online platforms. We show that our method is able to improve the quality of the wind power forecast issued by the Danish TSO by several percentage points (when measured in terms of the mean absolute or the root mean square error) and to significantly reduce the balancing costs incurred by the wind power producer. |
| Tasks | Decision Making |
| Published | 2019-07-17 |
| URL | https://arxiv.org/abs/1907.07580v3 |
| https://arxiv.org/pdf/1907.07580v3.pdf | |
| PWC | https://paperswithcode.com/paper/feature-driven-improvement-of-renewable |
| Repo | |
| Framework | |
Robust Opponent Modeling via Adversarial Ensemble Reinforcement Learning in Asymmetric Imperfect-Information Games
| Title | Robust Opponent Modeling via Adversarial Ensemble Reinforcement Learning in Asymmetric Imperfect-Information Games |
| Authors | Macheng Shen, Jonathan P. How |
| Abstract | This paper presents an algorithmic framework for learning robust policies in asymmetric imperfect-information games, where the joint reward could depend on the uncertain opponent type (a private information known only to the opponent itself and its ally). In order to maximize the reward, the protagonist agent has to infer the opponent type through agent modeling. We use multiagent reinforcement learning (MARL) to learn opponent models through self-play, which captures the full strategy interaction and reasoning between agents. However, agent policies learned from self-play can suffer from mutual overfitting. Ensemble training methods can be used to improve the robustness of agent policy against different opponents, but it also significantly increases the computational overhead. In order to achieve a good trade-off between the robustness of the learned policy and the computation complexity, we propose to train a separate opponent policy against the protagonist agent for evaluation purposes. The reward achieved by this opponent is a noisy measure of the robustness of the protagonist agent policy due to the intrinsic stochastic nature of a reinforcement learner. To handle this stochasticity, we apply a stochastic optimization scheme to dynamically update the opponent ensemble to optimize an objective function that strikes a balance between robustness and computation complexity. We empirically show that, under the same limited computational budget, the proposed method results in more robust policy learning than standard ensemble training. |
| Tasks | Stochastic Optimization |
| Published | 2019-09-18 |
| URL | https://arxiv.org/abs/1909.08735v4 |
| https://arxiv.org/pdf/1909.08735v4.pdf | |
| PWC | https://paperswithcode.com/paper/robust-opponent-modeling-via-adversarial |
| Repo | |
| Framework | |
True Parallel Graph Transformations: an Algebraic Approach Based on Weak Spans
| Title | True Parallel Graph Transformations: an Algebraic Approach Based on Weak Spans |
| Authors | Thierry Boy de la Tour, Rachid Echahed |
| Abstract | We address the problem of defining graph transformations by the simultaneous application of direct transformations even when these cannot be applied independently of each other. An algebraic approach is adopted, with production rules of the form $L\xleftarrow{l}K \xleftarrow{i} I \xrightarrow{r} R$, called weak spans. A parallel coherent transformation is introduced and shown to be a conservative extension of the interleaving semantics of parallel independent direct transformations. A categorical construction of finitely attributed structures is proposed, in which parallel coherent transformations can be built in a natural way. These notions are introduced and illustrated on detailed examples. |
| Tasks | |
| Published | 2019-04-17 |
| URL | http://arxiv.org/abs/1904.08850v1 |
| http://arxiv.org/pdf/1904.08850v1.pdf | |
| PWC | https://paperswithcode.com/paper/true-parallel-graph-transformations-an |
| Repo | |
| Framework | |
Predicting optimal value functions by interpolating reward functions in scalarized multi-objective reinforcement learning
| Title | Predicting optimal value functions by interpolating reward functions in scalarized multi-objective reinforcement learning |
| Authors | Arpan Kusari, Jonathan P. How |
| Abstract | A common approach for defining a reward function for Multi-objective Reinforcement Learning (MORL) problems is the weighted sum of the multiple objectives. The weights are then treated as design parameters dependent on the expertise (and preference) of the person performing the learning, with the typical result that a new solution is required for any change in these settings. This paper investigates the relationship between the reward function and the optimal value function for MORL; specifically addressing the question of how to approximate the optimal value function well beyond the set of weights for which the optimization problem was actually solved, thereby avoiding the need to recompute for any particular choice. We prove that the value function transforms smoothly given a transformation of weights of the reward function (and thus a smooth interpolation in the policy space). A Gaussian process is used to obtain a smooth interpolation over the reward function weights of the optimal value function for three well-known examples: GridWorld, Objectworld and Pendulum. The results show that the interpolation can provide very robust values for sample states and action space in discrete and continuous domain problems. Significant advantages arise from utilizing this interpolation technique in the domain of autonomous vehicles: easy, instant adaptation of user preferences while driving and true randomization of obstacle vehicle behavior preferences during training. |
| Tasks | Autonomous Vehicles |
| Published | 2019-09-11 |
| URL | https://arxiv.org/abs/1909.05004v4 |
| https://arxiv.org/pdf/1909.05004v4.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-optimal-value-functions-by |
| Repo | |
| Framework | |
Approximate policy iteration using neural networks for storage problems
| Title | Approximate policy iteration using neural networks for storage problems |
| Authors | Trivikram Dokka, Richlove Frimpong |
| Abstract | We consider the stochastic single node energy storage problem (SNES) and revisit Approximate Policy Iteration (API) to solve SNES. We show that the performance of API can be boosted by using neural networks as an approximation architecture at the policy evaluation stage. To achieve this, we use a model different to that in literature with aggregate variables reducing the dimensionality of the decision vector, which in turn makes it viable to use neural network predictions in the policy improvement stage. We show that performance improvement by neural networks is even more significant in the case when charging efficiency of storage systems is low. |
| Tasks | |
| Published | 2019-10-04 |
| URL | https://arxiv.org/abs/1910.01895v1 |
| https://arxiv.org/pdf/1910.01895v1.pdf | |
| PWC | https://paperswithcode.com/paper/approximate-policy-iteration-using-neural |
| Repo | |
| Framework | |
Anomaly detection in the dynamics of web and social networks
| Title | Anomaly detection in the dynamics of web and social networks |
| Authors | Volodymyr Miz, Benjamin Ricaud, Kirell Benzi, Pierre Vandergheynst |
| Abstract | In this work, we propose a new, fast and scalable method for anomaly detection in large time-evolving graphs. It may be a static graph with dynamic node attributes (e.g. time-series), or a graph evolving in time, such as a temporal network. We define an anomaly as a localized increase in temporal activity in a cluster of nodes. The algorithm is unsupervised. It is able to detect and track anomalous activity in a dynamic network despite the noise from multiple interfering sources. We use the Hopfield network model of memory to combine the graph and time information. We show that anomalies can be spotted with a good precision using a memory network. The presented approach is scalable and we provide a distributed implementation of the algorithm. To demonstrate its efficiency, we apply it to two datasets: Enron Email dataset and Wikipedia page views. We show that the anomalous spikes are triggered by the real-world events that impact the network dynamics. Besides, the structure of the clusters and the analysis of the time evolution associated with the detected events reveals interesting facts on how humans interact, exchange and search for information, opening the door to new quantitative studies on collective and social behavior on large and dynamic datasets. |
| Tasks | Anomaly Detection, Time Series |
| Published | 2019-01-22 |
| URL | http://arxiv.org/abs/1901.09688v1 |
| http://arxiv.org/pdf/1901.09688v1.pdf | |
| PWC | https://paperswithcode.com/paper/anomaly-detection-in-the-dynamics-of-web-and |
| Repo | |
| Framework | |
Finding Missing Children: Aging Deep Face Features
| Title | Finding Missing Children: Aging Deep Face Features |
| Authors | Debayan Deb, Divyansh Aggarwal, Anil K. Jain |
| Abstract | Given a gallery of face images of missing children, state-of-the-art face recognition systems fall short in identifying a child (probe) recovered at a later age. We propose an age-progression module that can age-progress deep face features output by any commodity face matcher. For time lapses larger than 10 years (the missing child is found after 10 or more years), the proposed age-progression module improves the closed-set identification accuracy of FaceNet from 40% to 49.56% and CosFace from 56.88% to 61.25% on a child celebrity dataset, namely ITWCC. The proposed method also outperforms state-of-the-art approaches with a rank-1 identification rate from 94.91% to 95.91% on a public aging dataset, FG-NET, and from 99.50% to 99.58% on CACD-VS. These results suggest that aging face features enhances the ability to identify young children who are possible victims of child trafficking or abduction. |
| Tasks | Face Recognition |
| Published | 2019-11-18 |
| URL | https://arxiv.org/abs/1911.07538v2 |
| https://arxiv.org/pdf/1911.07538v2.pdf | |
| PWC | https://paperswithcode.com/paper/aging-deep-face-features-finding-missing |
| Repo | |
| Framework | |
Does Face Recognition Accuracy Get Better With Age? Deep Face Matchers Say No
| Title | Does Face Recognition Accuracy Get Better With Age? Deep Face Matchers Say No |
| Authors | Vítor Albiero, Kevin W. Bowyer, Kushal Vangara, Michael C. King |
| Abstract | Previous studies generally agree that face recognition accuracy is higher for older persons than for younger persons. But most previous studies were before the wave of deep learning matchers, and most considered accuracy only in terms of the verification rate for genuine pairs. This paper investigates accuracy for age groups 16-29, 30-49 and 50-70, using three modern deep CNN matchers, and considers differences in the impostor and genuine distributions as well as verification rates and ROC curves. We find that accuracy is lower for older persons and higher for younger persons. In contrast, a pre deep learning matcher on the same dataset shows the traditional result of higher accuracy for older persons, although its overall accuracy is much lower than that of the deep learning matchers. Comparing the impostor and genuine distributions, we conclude that impostor scores have a larger effect than genuine scores in causing lower accuracy for the older age group. We also investigate the effects of training data across the age groups. Our results show that fine-tuning the deep CNN models on additional images of older persons actually lowers accuracy for the older age group. Also, we fine-tune and train from scratch two models using age-balanced training datasets, and these results also show lower accuracy for older age group. These results argue that the lower accuracy for the older age group is not due to imbalance in the original training data. |
| Tasks | Face Recognition |
| Published | 2019-11-14 |
| URL | https://arxiv.org/abs/1911.06396v1 |
| https://arxiv.org/pdf/1911.06396v1.pdf | |
| PWC | https://paperswithcode.com/paper/does-face-recognition-accuracy-get-better |
| Repo | |
| Framework | |
‘Warriors of the Word’ – Deciphering Lyrical Topics in Music and Their Connection to Audio Feature Dimensions Based on a Corpus of Over 100,000 Metal Songs
| Title | ‘Warriors of the Word’ – Deciphering Lyrical Topics in Music and Their Connection to Audio Feature Dimensions Based on a Corpus of Over 100,000 Metal Songs |
| Authors | Isabella Czedik-Eysenberg, Oliver Wieczorek, Christoph Reuter |
| Abstract | We look into the connection between the musical and lyrical content of metal music by combining automated extraction of high-level audio features and quantitative text analysis on a corpus of 124.288 song lyrics from this genre. Based on this text corpus, a topic model was first constructed using Latent Dirichlet Allocation (LDA). For a subsample of 503 songs, scores for predicting perceived musical hardness/heaviness and darkness/gloominess were extracted using audio feature models. By combining both audio feature and text analysis, we (1) offer a comprehensive overview of the lyrical topics present within the metal genre and (2) are able to establish whether or not levels of hardness and other music dimensions are associated with the occurrence of particularly harsh (and other) textual topics. Twenty typical topics were identified and projected into a topic space using multidimensional scaling (MDS). After Bonferroni correction, positive correlations were found between musical hardness and darkness and textual topics dealing with ‘brutal death’, ‘dystopia’, ‘archaisms and occultism’, ‘religion and satanism’, ‘battle’ and ‘(psychological) madness’, while there is a negative associations with topics like ‘personal life’ and ‘love and romance’. |
| Tasks | |
| Published | 2019-11-12 |
| URL | https://arxiv.org/abs/1911.04952v2 |
| https://arxiv.org/pdf/1911.04952v2.pdf | |
| PWC | https://paperswithcode.com/paper/warriors-of-the-word-deciphering-lyrical |
| Repo | |
| Framework | |
92c/MFlops/s, Ultra-Large-Scale Neural-Network Training on a PIII Cluster
| Title | 92c/MFlops/s, Ultra-Large-Scale Neural-Network Training on a PIII Cluster |
| Authors | Douglas Aberdeen, Jonathan Baxter, Robert Edwards |
| Abstract | Artificial neural networks with millions of adjustable parameters and a similar number of training examples are a potential solution for difficult, large-scale pattern recognition problems in areas such as speech and face recognition, classification of large volumes of web data, and finance. The bottleneck is that neural network training involves iterative gradient descent and is extremely computationally intensive. In this paper we present a technique for distributed training of Ultra Large Scale Neural Networks (ULSNN) on Bunyip, a Linux-based cluster of 196 Pentium III processors. To illustrate ULSNN training we describe an experiment in which a neural network with 1.73 million adjustable parameters was trained to recognize machine-printed Japanese characters from a database containing 9 million training patterns. The training runs with a average performance of 163.3 GFlops/s (single precision). With a machine cost of $150,913, this yields a price/performance ratio of 92.4c/MFlops/s (single precision). For comparison purposes, training using double precision and the ATLAS DGEMM produces a sustained performance of 70 MFlops/s or $2.16 / MFlop/s (double precision). |
| Tasks | Face Recognition |
| Published | 2019-11-12 |
| URL | https://arxiv.org/abs/1911.05181v1 |
| https://arxiv.org/pdf/1911.05181v1.pdf | |
| PWC | https://paperswithcode.com/paper/92cmflopss-ultra-large-scale-neural-network |
| Repo | |
| Framework | |
On Machine Learning DoS Attack Identification from Cloud Computing Telemetry
| Title | On Machine Learning DoS Attack Identification from Cloud Computing Telemetry |
| Authors | João Henrique Corrêa, Patrick Marques Ciarelli, Moises R. N. Ribeiro, Rodolfo da Silva Villaca |
| Abstract | The detection of Denial of Service (DoS) attacks remains a challenge for the cloud environment, affecting a massive number of services and applications hosted by such virtualized infrastructures. Typically, in the literature, the detection of DoS attacks is performed solely by analyzing the traffic of packets in the network. This work advocates for the use of telemetry from the cloud to detect DoS attacks using Machine Learning algorithms. Our hypothesis is based on richness of such native data collection services, with metrics from both physical and virtual hosts. Our preliminary results demonstrate that DoS can be identified accurately with k-Nearest Neighbors (kNN) and decision tree (CART). |
| Tasks | |
| Published | 2019-04-11 |
| URL | http://arxiv.org/abs/1904.06211v1 |
| http://arxiv.org/pdf/1904.06211v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-machine-learning-dos-attack-identification |
| Repo | |
| Framework | |
