Paper Group ANR 1563
A Semantic Approach for User-Brand Targeting in On-Line Social Networks. Reinforcement Learning: Prediction, Control and Value Function Approximation. The information-theoretic value of unlabeled data in semi-supervised learning. Perception of visual numerosity in humans and machines. Session-based Sequential Skip Prediction via Recurrent Neural Ne …
A Semantic Approach for User-Brand Targeting in On-Line Social Networks
| Title | A Semantic Approach for User-Brand Targeting in On-Line Social Networks |
| Authors | Mariella Bonomo, Gaspare Ciaccio, Andrea De Salve, Simona E. Rombo |
| Abstract | We propose a general framework for the recommendation of possible customers (users) to advertisers (e.g., brands) based on the comparison between On-line Social Network profiles. In particular, we represent both user and brand profiles as trees where nodes correspond to categories and sub-categories in the associated On-line Social Network. When categories involve posts and comments, the comparison is based on word embedding, and this allows to take into account the similarity between topics popular in the brand profile and user preferences. Results on real datasets show that our approach is successfull in identifying the most suitable set of users to be used as target for a given advertisement campaign. |
| Tasks | |
| Published | 2019-07-02 |
| URL | https://arxiv.org/abs/1907.01326v1 |
| https://arxiv.org/pdf/1907.01326v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-semantic-approach-for-user-brand-targeting |
| Repo | |
| Framework | |
Reinforcement Learning: Prediction, Control and Value Function Approximation
| Title | Reinforcement Learning: Prediction, Control and Value Function Approximation |
| Authors | Haoqian Li, Thomas Lau |
| Abstract | With the increasing power of computers and the rapid development of self-learning methodologies such as machine learning and artificial intelligence, the problem of constructing an automatic Financial Trading Systems (FTFs) becomes an increasingly attractive research topic. An intuitive way of developing such a trading algorithm is to use Reinforcement Learning (RL) algorithms, which does not require model-building. In this paper, we dive into the RL algorithms and illustrate the definitions of the reward function, actions and policy functions in details, as well as introducing algorithms that could be applied to FTFs. |
| Tasks | |
| Published | 2019-08-28 |
| URL | https://arxiv.org/abs/1908.10771v1 |
| https://arxiv.org/pdf/1908.10771v1.pdf | |
| PWC | https://paperswithcode.com/paper/reinforcement-learning-prediction-control-and |
| Repo | |
| Framework | |
The information-theoretic value of unlabeled data in semi-supervised learning
| Title | The information-theoretic value of unlabeled data in semi-supervised learning |
| Authors | Alexander Golovnev, Dávid Pál, Balázs Szörényi |
| Abstract | We quantify the separation between the numbers of labeled examples required to learn in two settings: Settings with and without the knowledge of the distribution of the unlabeled data. More specifically, we prove a separation by $\Theta(\log n)$ multiplicative factor for the class of projections over the Boolean hypercube of dimension $n$. We prove that there is no separation for the class of all functions on domain of any size. Learning with the knowledge of the distribution (a.k.a. fixed-distribution learning) can be viewed as an idealized scenario of semi-supervised learning where the number of unlabeled data points is so great that the unlabeled distribution is known exactly. For this reason, we call the separation the value of unlabeled data. |
| Tasks | |
| Published | 2019-01-16 |
| URL | https://arxiv.org/abs/1901.05515v2 |
| https://arxiv.org/pdf/1901.05515v2.pdf | |
| PWC | https://paperswithcode.com/paper/the-information-theoretic-value-of-unlabeled |
| Repo | |
| Framework | |
Perception of visual numerosity in humans and machines
| Title | Perception of visual numerosity in humans and machines |
| Authors | Alberto Testolin, Serena Dolfi, Mathijs Rochus, Marco Zorzi |
| Abstract | Numerosity perception is foundational to mathematical learning, but its computational bases are strongly debated. Some investigators argue that humans are endowed with a specialized system supporting numerical representation; others argue that visual numerosity is estimated using continuous magnitudes, such as density or area, which usually co-vary with number. Here we reconcile these contrasting perspectives by testing deep networks on the same numerosity comparison task that was administered to humans, using a stimulus space that allows to measure the contribution of non-numerical features. Our model accurately simulated the psychophysics of numerosity perception and the associated developmental changes: discrimination was driven by numerosity information, but non-numerical features had a significant impact, especially early during development. Representational similarity analysis further highlighted that both numerosity and continuous magnitudes were spontaneously encoded even when no task had to be carried out, demonstrating that numerosity is a major, salient property of our visual environment. |
| Tasks | |
| Published | 2019-07-16 |
| URL | https://arxiv.org/abs/1907.06996v1 |
| https://arxiv.org/pdf/1907.06996v1.pdf | |
| PWC | https://paperswithcode.com/paper/perception-of-visual-numerosity-in-humans-and |
| Repo | |
| Framework | |
Session-based Sequential Skip Prediction via Recurrent Neural Networks
| Title | Session-based Sequential Skip Prediction via Recurrent Neural Networks |
| Authors | Lin Zhu, Yihong Chen |
| Abstract | The focus of WSDM cup 2019 is session-based sequential skip prediction, i.e. predicting whether users will skip tracks, given their immediately preceding interactions in their listening session. This paper provides the solution of our team \textbf{ekffar} to this challenge. We focus on recurrent-neural-network-based deep learning approaches which have previously been shown to perform well on session-based recommendation problems. We show that by choosing an appropriate recurrent architecture that properly accounts for the given information such as user interaction features and song metadata, a single neural network could achieve a Mean Average Accuracy (AA) score of 0.648 on the withheld test data. Meanwhile, by ensembling several variants of the core model, the overall recommendation accuracy can be improved even further. By using the proposed approach, our team was able to attain the 1st place in the competition. We have open-sourced our implementation at GitHub. |
| Tasks | Session-Based Recommendations |
| Published | 2019-02-13 |
| URL | http://arxiv.org/abs/1902.04743v1 |
| http://arxiv.org/pdf/1902.04743v1.pdf | |
| PWC | https://paperswithcode.com/paper/session-based-sequential-skip-prediction-via |
| Repo | |
| Framework | |
Simultaneously Learning Vision and Feature-based Control Policies for Real-world Ball-in-a-Cup
| Title | Simultaneously Learning Vision and Feature-based Control Policies for Real-world Ball-in-a-Cup |
| Authors | Devin Schwab, Tobias Springenberg, Murilo F. Martins, Thomas Lampe, Michael Neunert, Abbas Abdolmaleki, Tim Hertweck, Roland Hafner, Francesco Nori, Martin Riedmiller |
| Abstract | We present a method for fast training of vision based control policies on real robots. The key idea behind our method is to perform multi-task Reinforcement Learning with auxiliary tasks that differ not only in the reward to be optimized but also in the state-space in which they operate. In particular, we allow auxiliary task policies to utilize task features that are available only at training-time. This allows for fast learning of auxiliary policies, which subsequently generate good data for training the main, vision-based control policies. This method can be seen as an extension of the Scheduled Auxiliary Control (SAC-X) framework. We demonstrate the efficacy of our method by using both a simulated and real-world Ball-in-a-Cup game controlled by a robot arm. In simulation, our approach leads to significant learning speed-ups when compared to standard SAC-X. On the real robot we show that the task can be learned from-scratch, i.e., with no transfer from simulation and no imitation learning. Videos of our learned policies running on the real robot can be found at https://sites.google.com/view/rss-2019-sawyer-bic/. |
| Tasks | Imitation Learning |
| Published | 2019-02-13 |
| URL | http://arxiv.org/abs/1902.04706v2 |
| http://arxiv.org/pdf/1902.04706v2.pdf | |
| PWC | https://paperswithcode.com/paper/simultaneously-learning-vision-and-feature |
| Repo | |
| Framework | |
Modeling Severe Traffic Accidents With Spatial And Temporal Features
| Title | Modeling Severe Traffic Accidents With Spatial And Temporal Features |
| Authors | Devashish Khulbe, Soumya Sourav |
| Abstract | We present an approach to estimate the severity of traffic related accidents in aggregated (area-level) and disaggregated (point level) data. Exploring spatial features, we measure complexity of road networks using several area level variables. Also using temporal and other situational features from open data for New York City, we use Gradient Boosting models for inference and measuring feature importance along with Gaussian Processes to model spatial dependencies in the data. The results show significant importance of complexity in aggregated model as well as as other features in prediction which may be helpful in framing policies and targeting interventions for preventing severe traffic related accidents and injuries. |
| Tasks | Feature Importance, Gaussian Processes |
| Published | 2019-06-25 |
| URL | https://arxiv.org/abs/1906.10317v1 |
| https://arxiv.org/pdf/1906.10317v1.pdf | |
| PWC | https://paperswithcode.com/paper/modeling-severe-traffic-accidents-with |
| Repo | |
| Framework | |
Scheduled Intrinsic Drive: A Hierarchical Take on Intrinsically Motivated Exploration
| Title | Scheduled Intrinsic Drive: A Hierarchical Take on Intrinsically Motivated Exploration |
| Authors | Jingwei Zhang, Niklas Wetzel, Nicolai Dorka, Joschka Boedecker, Wolfram Burgard |
| Abstract | Exploration in sparse reward reinforcement learning remains an open challenge. Many state-of-the-art methods use intrinsic motivation to complement the sparse extrinsic reward signal, giving the agent more opportunities to receive feedback during exploration. Commonly these signals are added as bonus rewards, which results in a mixture policy that neither conducts exploration nor task fulfillment resolutely. In this paper, we instead learn separate intrinsic and extrinsic task policies and schedule between these different drives to accelerate exploration and stabilize learning. Moreover, we introduce a new type of intrinsic reward denoted as successor feature control (SFC), which is general and not task-specific. It takes into account statistics over complete trajectories and thus differs from previous methods that only use local information to evaluate intrinsic motivation. We evaluate our proposed scheduled intrinsic drive (SID) agent using three different environments with pure visual inputs: VizDoom, DeepMind Lab and DeepMind Control Suite. The results show a substantially improved exploration efficiency with SFC and the hierarchical usage of the intrinsic drives. A video of our experimental results can be found at https://youtu.be/b0MbY3lUlEI. |
| Tasks | |
| Published | 2019-03-18 |
| URL | https://arxiv.org/abs/1903.07400v2 |
| https://arxiv.org/pdf/1903.07400v2.pdf | |
| PWC | https://paperswithcode.com/paper/scheduled-intrinsic-drive-a-hierarchical-take |
| Repo | |
| Framework | |
Preliminary Systematic Literature Review of Machine Learning System Development Process
| Title | Preliminary Systematic Literature Review of Machine Learning System Development Process |
| Authors | Yasuhiro Watanabe, Hironori Washizaki, Kazunori Sakamoto, Daisuke Saito, Kiyoshi Honda, Naohiko Tsuda, Yoshiaki Fukazawa, Nobukazu Yoshioka |
| Abstract | Previous machine learning (ML) system development research suggests that emerging software quality attributes are a concern due to the probabilistic behavior of ML systems. Assuming that detailed development processes depend on individual developers and are not discussed in detail. To help developers to standardize their ML system development processes, we conduct a preliminary systematic literature review on ML system development processes. A search query of 2358 papers identified 7 papers as well as two other papers determined in an ad-hoc review. Our findings include emphasized phases in ML system developments, frequently described practices and tailored traditional software development practices. |
| Tasks | |
| Published | 2019-10-12 |
| URL | https://arxiv.org/abs/1910.05528v1 |
| https://arxiv.org/pdf/1910.05528v1.pdf | |
| PWC | https://paperswithcode.com/paper/preliminary-systematic-literature-review-of |
| Repo | |
| Framework | |
Shallow Domain Adaptive Embeddings for Sentiment Analysis
| Title | Shallow Domain Adaptive Embeddings for Sentiment Analysis |
| Authors | Prathusha K Sarma, Yingyu Liang, William A Sethares |
| Abstract | This paper proposes a way to improve the performance of existing algorithms for text classification in domains with strong language semantics. We propose a domain adaptation layer learns weights to combine a generic and a domain specific (DS) word embedding into a domain adapted (DA) embedding. The DA word embeddings are then used as inputs to a generic encoder + classifier framework to perform a downstream task such as classification. This adaptation layer is particularly suited to datasets that are modest in size, and which are, therefore, not ideal candidates for (re)training a deep neural network architecture. Results on binary and multi-class classification tasks using popular encoder architectures, including current state-of-the-art methods (with and without the shallow adaptation layer) show the effectiveness of the proposed approach. |
| Tasks | Domain Adaptation, Sentiment Analysis, Text Classification, Word Embeddings |
| Published | 2019-08-16 |
| URL | https://arxiv.org/abs/1908.06082v1 |
| https://arxiv.org/pdf/1908.06082v1.pdf | |
| PWC | https://paperswithcode.com/paper/shallow-domain-adaptive-embeddings-for |
| Repo | |
| Framework | |
Fully Convolutional Networks for Handwriting Recognition
| Title | Fully Convolutional Networks for Handwriting Recognition |
| Authors | Felipe Petroski Such, Dheeraj Peri, Frank Brockler, Paul Hutkowski, Raymond Ptucha |
| Abstract | Handwritten text recognition is challenging because of the virtually infinite ways a human can write the same message. Our fully convolutional handwriting model takes in a handwriting sample of unknown length and outputs an arbitrary stream of symbols. Our dual stream architecture uses both local and global context and mitigates the need for heavy preprocessing steps such as symbol alignment correction as well as complex post processing steps such as connectionist temporal classification, dictionary matching or language models. Using over 100 unique symbols, our model is agnostic to Latin-based languages, and is shown to be quite competitive with state of the art dictionary based methods on the popular IAM and RIMES datasets. When a dictionary is known, we further allow a probabilistic character error rate to correct errant word blocks. Finally, we introduce an attention based mechanism which can automatically target variants of handwriting, such as slant, stroke width, or noise. |
| Tasks | |
| Published | 2019-07-10 |
| URL | https://arxiv.org/abs/1907.04888v1 |
| https://arxiv.org/pdf/1907.04888v1.pdf | |
| PWC | https://paperswithcode.com/paper/fully-convolutional-networks-for-handwriting |
| Repo | |
| Framework | |
WinoGrande: An Adversarial Winograd Schema Challenge at Scale
| Title | WinoGrande: An Adversarial Winograd Schema Challenge at Scale |
| Authors | Keisuke Sakaguchi, Ronan Le Bras, Chandra Bhagavatula, Yejin Choi |
| Abstract | The Winograd Schema Challenge (WSC) (Levesque, Davis, and Morgenstern 2011), a benchmark for commonsense reasoning, is a set of 273 expert-crafted pronoun resolution problems originally designed to be unsolvable for statistical models that rely on selectional preferences or word associations. However, recent advances in neural language models have already reached around 90% accuracy on variants of WSC. This raises an important question whether these models have truly acquired robust commonsense capabilities or whether they rely on spurious biases in the datasets that lead to an overestimation of the true capabilities of machine commonsense. To investigate this question, we introduce WinoGrande, a large-scale dataset of 44k problems, inspired by the original WSC design, but adjusted to improve both the scale and the hardness of the dataset. The key steps of the dataset construction consist of (1) a carefully designed crowdsourcing procedure, followed by (2) systematic bias reduction using a novel AfLite algorithm that generalizes human-detectable word associations to machine-detectable embedding associations. The best state-of-the-art methods on WinoGrande achieve 59.4-79.1%, which are 15-35% below human performance of 94.0%, depending on the amount of the training data allowed. Furthermore, we establish new state-of-the-art results on five related benchmarks - WSC (90.1%), DPR (93.1%), COPA (90.6%), KnowRef (85.6%), and Winogender (97.1%). These results have dual implications: on one hand, they demonstrate the effectiveness of WinoGrande when used as a resource for transfer learning. On the other hand, they raise a concern that we are likely to be overestimating the true capabilities of machine commonsense across all these benchmarks. We emphasize the importance of algorithmic bias reduction in existing and future benchmarks to mitigate such overestimation. |
| Tasks | Transfer Learning |
| Published | 2019-07-24 |
| URL | https://arxiv.org/abs/1907.10641v2 |
| https://arxiv.org/pdf/1907.10641v2.pdf | |
| PWC | https://paperswithcode.com/paper/winogrande-an-adversarial-winograd-schema |
| Repo | |
| Framework | |
On the Tour Towards DPLL(MAPF) and Beyond
| Title | On the Tour Towards DPLL(MAPF) and Beyond |
| Authors | Pavel Surynek |
| Abstract | We discuss milestones on the tour towards DPLL(MAPF), a multi-agent path finding (MAPF) solver fully integrated with the Davis-Putnam-Logemann-Loveland (DPLL) propositional satisfiability testing algorithm through satisfiability modulo theories (SMT). The task in MAPF is to navigate agents in an undirected graph in a non-colliding way so that each agent eventually reaches its unique goal vertex. At most one agent can reside in a vertex at a time. Agents can move instantaneously by traversing edges provided the movement does not result in a collision. Recently attempts to solve MAPF optimally w.r.t. the sum-of-costs or the makespan based on the reduction of MAPF to propositional satisfiability (SAT) have appeared. The most successful methods rely on building the propositional encoding for the given MAPF instance lazily by a process inspired in the SMT paradigm. The integration of satisfiability testing by the SAT solver and the high-level construction of the encoding is however relatively loose in existing methods. Therefore the ultimate goal of research in this direction is to build the DPLL(MAPF) algorithm, a MAPF solver where the construction of the encoding is fully integrated with the underlying SAT solver. We discuss the current state-of-the-art in MAPF solving and what steps need to be done to get DPLL(MAPF). The advantages of DPLL(MAPF) in terms of its potential to be alternatively parametrized with MAPF$^R$, a theory of continuous MAPF with geometric agents, are also discussed. |
| Tasks | Multi-Agent Path Finding |
| Published | 2019-07-11 |
| URL | https://arxiv.org/abs/1907.07631v1 |
| https://arxiv.org/pdf/1907.07631v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-tour-towards-dpllmapf-and-beyond |
| Repo | |
| Framework | |
Fast Hierarchical Depth Map Computation from Stereo
| Title | Fast Hierarchical Depth Map Computation from Stereo |
| Authors | Vinay Kaushik, Brejesh Lall |
| Abstract | Disparity by Block Matching stereo is usually used in applications with limited computational power in order to get depth estimates. However, the research on simple stereo methods has been lesser than the energy based counterparts which promise a better quality depth map with more potential for future improvements. Semi-global-matching (SGM) methods offer good performance and easy implementation but suffer from the problem of very high memory footprint because it’s working on the full disparity space image. On the other hand, Block matching stereo needs much less memory. In this paper, we introduce a novel multi-scale-hierarchical block-matching approach using a pyramidal variant of depth and cost functions which drastically improves the results of standard block matching stereo techniques while preserving the low memory footprint and further reducing the complexity of standard block matching. We tested our new multi block matching scheme on the Middlebury stereo benchmark. For the Middlebury benchmark we get results that are only slightly worse than state of the art SGM implementations. |
| Tasks | |
| Published | 2019-01-28 |
| URL | http://arxiv.org/abs/1901.09593v1 |
| http://arxiv.org/pdf/1901.09593v1.pdf | |
| PWC | https://paperswithcode.com/paper/fast-hierarchical-depth-map-computation-from |
| Repo | |
| Framework | |
Aerial Animal Biometrics: Individual Friesian Cattle Recovery and Visual Identification via an Autonomous UAV with Onboard Deep Inference
| Title | Aerial Animal Biometrics: Individual Friesian Cattle Recovery and Visual Identification via an Autonomous UAV with Onboard Deep Inference |
| Authors | William Andrew, Colin Greatwood, Tilo Burghardt |
| Abstract | This paper describes a computationally-enhanced M100 UAV platform with an onboard deep learning inference system for integrated computer vision and navigation able to autonomously find and visually identify by coat pattern individual Holstein Friesian cattle in freely moving herds. We propose an approach that utilises three deep convolutional neural network architectures running live onboard the aircraft; that is, a YoloV2-based species detector, a dual-stream CNN delivering exploratory agency and an InceptionV3-based biometric LRCN for individual animal identification. We evaluate the performance of each of the components offline, and also online via real-world field tests comprising 146.7 minutes of autonomous low altitude flight in a farm environment over a dispersed herd of 17 heifer dairy cows. We report error-free identification performance on this online experiment. The presented proof-of-concept system is the first of its kind and a successful step towards autonomous biometric identification of individual animals from the air in open pasture environments for tag-less AI support in farming and ecology. |
| Tasks | |
| Published | 2019-07-11 |
| URL | https://arxiv.org/abs/1907.05310v1 |
| https://arxiv.org/pdf/1907.05310v1.pdf | |
| PWC | https://paperswithcode.com/paper/aerial-animal-biometrics-individual-friesian |
| Repo | |
| Framework | |
