Paper Group ANR 959
Quantum Learning Boolean Linear Functions w.r.t. Product Distributions. Query Term Weighting based on Query Performance Prediction. Machine Learning Methods for Shark Detection. Bidirectional Recurrent Models for Offensive Tweet Classification. DRD-Net: Detail-recovery Image Deraining via Context Aggregation Networks. On-Device User Intent Predicti …
Quantum Learning Boolean Linear Functions w.r.t. Product Distributions
| Title | Quantum Learning Boolean Linear Functions w.r.t. Product Distributions |
| Authors | Matthias C. Caro |
| Abstract | The problem of learning Boolean linear functions from quantum examples w.r.t. the uniform distribution can be solved on a quantum computer using the Bernstein-Vazirani algorithm. A similar strategy can be applied in the case of noisy quantum training data, as was observed in arXiv:1702.08255v2 [quant-ph]. We employ the biased quantum Fourier transform introduced in arXiv:1802.05690v2 [quant-ph] to develop quantum algorithms for learning Boolean linear functions from quantum examples w.r.t. a biased product distribution. Here, one procedure is applicable to any (except full) bias, the other gives a better performance but is applicable only for small bias. Moreover, we discuss the stability of the second procedure w.r.t. noisy training data and w.r.t. faulty quantum gates. The latter also enables us to solve a version of the problem where the underlying distribution is not known in advance. Finally, we prove lower bounds on the classical and quantum sample complexities of the learning problem and compare these to the upper bounds implied by our algorithms. |
| Tasks | |
| Published | 2019-02-23 |
| URL | http://arxiv.org/abs/1902.08753v1 |
| http://arxiv.org/pdf/1902.08753v1.pdf | |
| PWC | https://paperswithcode.com/paper/quantum-learning-boolean-linear-functions-wrt |
| Repo | |
| Framework | |
Query Term Weighting based on Query Performance Prediction
| Title | Query Term Weighting based on Query Performance Prediction |
| Authors | Haggai Roitman |
| Abstract | This work presents a general query term weighting approach based on query performance prediction (QPP). To this end, a given term is weighed according to its predicted effect on query performance. Such an effect is assumed to be manifested in the responses made by the underlying retrieval method for the original query and its (simple) variants in the form of a single-term expanded query. Focusing on search re-ranking as the underlying application, the effectiveness of the proposed term weighting approach is demonstrated using several state-of-the-art QPP methods evaluated over TREC corpora. |
| Tasks | |
| Published | 2019-02-27 |
| URL | http://arxiv.org/abs/1902.10371v1 |
| http://arxiv.org/pdf/1902.10371v1.pdf | |
| PWC | https://paperswithcode.com/paper/query-term-weighting-based-on-query |
| Repo | |
| Framework | |
Machine Learning Methods for Shark Detection
| Title | Machine Learning Methods for Shark Detection |
| Authors | Jordan F. Masakuna |
| Abstract | This essay reviews human observer-based methods employed in shark spotting in Muizenberg Beach. It investigates Machine Learning methods for automated shark detection with the aim of enhancing human observation. A questionnaire and interview were used to collect information about shark spotting, the motivation of the actual Shark Spotter program and its limitations. We have defined a list of desirable properties for our model and chosen the adequate mathematical techniques. The preliminary results of the research show that we can expect to extract useful information from shark images despite the geometric transformations that sharks perform, its features do not change. To conclude, we have partially implemented our model; the remaining implementation requires dataset. |
| Tasks | |
| Published | 2019-05-21 |
| URL | https://arxiv.org/abs/1905.13309v1 |
| https://arxiv.org/pdf/1905.13309v1.pdf | |
| PWC | https://paperswithcode.com/paper/190513309 |
| Repo | |
| Framework | |
Bidirectional Recurrent Models for Offensive Tweet Classification
| Title | Bidirectional Recurrent Models for Offensive Tweet Classification |
| Authors | Aleix Cambray, Norbert Podsadowski |
| Abstract | In this paper we propose four deep recurrent architectures to tackle the task of offensive tweet detection as well as further classification into targeting and subject of said targeting. Our architectures are based on LSTMs and GRUs, we present a simple bidirectional LSTM as a baseline system and then further increase the complexity of the models by adding convolutional layers and implementing a split-process-merge architecture with LSTM and GRU as processors. Multiple pre-processing techniques were also investigated. The validation F1-score results from each model are presented for the three subtasks as well as the final F1-score performance on the private competition test set. It was found that model complexity did not necessarily yield better results. Our best-performing model was also the simplest, a bidirectional LSTM; closely followed by a two-branch bidirectional LSTM and GRU architecture. |
| Tasks | |
| Published | 2019-03-19 |
| URL | http://arxiv.org/abs/1903.08808v1 |
| http://arxiv.org/pdf/1903.08808v1.pdf | |
| PWC | https://paperswithcode.com/paper/bidirectional-recurrent-models-for-offensive |
| Repo | |
| Framework | |
DRD-Net: Detail-recovery Image Deraining via Context Aggregation Networks
| Title | DRD-Net: Detail-recovery Image Deraining via Context Aggregation Networks |
| Authors | Sen Deng, Mingqiang Wei, Jun Wang, Luming Liang, Haoran Xie, Meng Wang |
| Abstract | Image deraining is a fundamental, yet not well-solved problem in computer vision and graphics. The traditional image deraining approaches commonly behave ineffectively in medium and heavy rain removal, while the learning-based ones lead to image degradations such as the loss of image details, halo artifacts and/or color distortion. Unlike existing image deraining approaches that lack the detail-recovery mechanism, we propose an end-to-end detail-recovery image deraining network (termed a DRD-Net) for single images. We for the first time introduce two sub-networks with a comprehensive loss function which synergize to derain and recover the lost details caused by deraining. We have three key contributions. First, we present a rain residual network to remove rain streaks from the rainy images, which combines the squeeze-and-excitation (SE) operation with residual blocks to make full advantage of spatial contextual information. Second, we design a new connection style block, named structure detail context aggregation block (SDCAB), which aggregates context feature information and has a large reception field. Third, benefiting from the SDCAB, we construct a detail repair network to encourage the lost details to return for eliminating image degradations. We have validated our approach on four recognized datasets (three synthetic and one real-world). Both quantitative and qualitative comparisons show that our approach outperforms the state-of-the-art deraining methods in terms of the deraining robustness and detail accuracy. The source code has been available for public evaluation and use on GitHub. |
| Tasks | Rain Removal |
| Published | 2019-08-27 |
| URL | https://arxiv.org/abs/1908.10267v2 |
| https://arxiv.org/pdf/1908.10267v2.pdf | |
| PWC | https://paperswithcode.com/paper/drd-net-detail-recovery-image-deraining-via |
| Repo | |
| Framework | |
On-Device User Intent Prediction for Context and Sequence Aware Recommendation
| Title | On-Device User Intent Prediction for Context and Sequence Aware Recommendation |
| Authors | Benu Madhab Changmai, Divija Nagaraju, Debi Prasanna Mohanty, Kriti Singh, Kunal Bansal, Sukumar Moharana |
| Abstract | The pursuit of improved accuracy in recommender systems has led to the incorporation of user context. Context-aware recommender systems typically handle large amounts of data which must be uploaded and stored on the cloud, putting the user’s personal information at risk. While there have been previous studies on privacy-sensitive and context-aware recommender systems, there has not been a full-fledged system deployed in an isolated mobile environment. We propose a secure and efficient on-device mechanism to predict a user’s next intention. The knowledge of the user’s real-time intention can help recommender systems to provide more relevant recommendations at the right moment. Our proposed algorithm is both context and sequence aware. We embed user intentions as weighted nodes in an n-dimensional vector space where each dimension represents a specific user context factor. Through a neighborhood searching method followed by a sequence matching algorithm, we search for the most relevant node to make the prediction. An evaluation of our methodology was done on a diverse real-world dataset where it was able to address practical scenarios like behavior drifts and sequential patterns efficiently and robustly. Our system also outperformed most of the state-of-the-art methods when evaluated for a similar problem domain on standard datasets. |
| Tasks | Recommendation Systems |
| Published | 2019-09-18 |
| URL | https://arxiv.org/abs/1909.12756v1 |
| https://arxiv.org/pdf/1909.12756v1.pdf | |
| PWC | https://paperswithcode.com/paper/on-device-user-intent-prediction-for-context |
| Repo | |
| Framework | |
Visual Person Understanding through Multi-Task and Multi-Dataset Learning
| Title | Visual Person Understanding through Multi-Task and Multi-Dataset Learning |
| Authors | Kilian Pfeiffer, Alexander Hermans, István Sárándi, Mark Weber, Bastian Leibe |
| Abstract | We address the problem of learning a single model for person re-identification, attribute classification, body part segmentation, and pose estimation. With predictions for these tasks we gain a more holistic understanding of persons, which is valuable for many applications. This is a classical multi-task learning problem. However, no dataset exists that these tasks could be jointly learned from. Hence several datasets need to be combined during training, which in other contexts has often led to reduced performance in the past. We extensively evaluate how the different task and datasets influence each other and how different degrees of parameter sharing between the tasks affect performance. Our final model matches or outperforms its single-task counterparts without creating significant computational overhead, rendering it highly interesting for resource-constrained scenarios such as mobile robotics. |
| Tasks | Multi-Task Learning, Person Re-Identification, Pose Estimation |
| Published | 2019-06-07 |
| URL | https://arxiv.org/abs/1906.03019v1 |
| https://arxiv.org/pdf/1906.03019v1.pdf | |
| PWC | https://paperswithcode.com/paper/visual-person-understanding-through-multi |
| Repo | |
| Framework | |
CASE: Context-Aware Semantic Expansion
| Title | CASE: Context-Aware Semantic Expansion |
| Authors | Jialong Han, Aixin Sun, Haisong Zhang, Chenliang Li, Shuming Shi |
| Abstract | In this paper, we define and study a new task called Context-Aware Semantic Expansion (CASE). Given a seed term in a sentential context, we aim to suggest other terms that well fit the context as the seed. CASE has many interesting applications such as query suggestion, computer-assisted writing, and word sense disambiguation, to name a few. Previous explorations, if any, only involve some similar tasks, and all require human annotations for evaluation. In this study, we demonstrate that annotations for this task can be harvested at scale from existing corpora, in a fully automatic manner. On a dataset of 1.8 million sentences thus derived, we propose a network architecture that encodes the context and seed term separately before suggesting alternative terms. The context encoder in this architecture can be easily extended by incorporating seed-aware attention. Our experiments demonstrate that competitive results are achieved with appropriate choices of context encoder and attention scoring function. |
| Tasks | Word Sense Disambiguation |
| Published | 2019-12-31 |
| URL | https://arxiv.org/abs/1912.13194v1 |
| https://arxiv.org/pdf/1912.13194v1.pdf | |
| PWC | https://paperswithcode.com/paper/case-context-aware-semantic-expansion |
| Repo | |
| Framework | |
Defending via strategic ML selection
| Title | Defending via strategic ML selection |
| Authors | Eitan Farchi, Onn Shehory, Guy Barash |
| Abstract | The results of a learning process depend on the input data. There are cases in which an adversary can strategically tamper with the input data to affect the outcome of the learning process. While some datasets are difficult to attack, many others are susceptible to manipulation. A resourceful attacker can tamper with large portions of the dataset and affect them. An attacker can additionally strategically focus on a preferred subset of the attributes in the dataset to maximize the effectiveness of the attack and minimize the resources allocated to data manipulation. In light of this vulnerability, we introduce a solution according to which the defender implements an array of learners, and their activation is performed strategically. The defender computes the (game theoretic) strategy space and accordingly applies a dominant strategy where possible, and a Nash-stable strategy otherwise. In this paper we provide the details of this approach. We analyze Nash equilibrium in such a strategic learning environment, and demonstrate our solution by specific examples. |
| Tasks | |
| Published | 2019-01-16 |
| URL | http://arxiv.org/abs/1904.00737v1 |
| http://arxiv.org/pdf/1904.00737v1.pdf | |
| PWC | https://paperswithcode.com/paper/defending-via-strategic-ml-selection |
| Repo | |
| Framework | |
Neural Networks as Explicit Word-Based Rules
| Title | Neural Networks as Explicit Word-Based Rules |
| Authors | Jindřich Libovický |
| Abstract | Filters of convolutional networks used in computer vision are often visualized as image patches that maximize the response of the filter. We use the same approach to interpret weight matrices in simple architectures for natural language processing tasks. We interpret a convolutional network for sentiment classification as word-based rules. Using the rule, we recover the performance of the original model. |
| Tasks | Sentiment Analysis |
| Published | 2019-07-10 |
| URL | https://arxiv.org/abs/1907.04613v1 |
| https://arxiv.org/pdf/1907.04613v1.pdf | |
| PWC | https://paperswithcode.com/paper/neural-networks-as-explicit-word-based-rules |
| Repo | |
| Framework | |
Attentive Student Meets Multi-Task Teacher: Improved Knowledge Distillation for Pretrained Models
| Title | Attentive Student Meets Multi-Task Teacher: Improved Knowledge Distillation for Pretrained Models |
| Authors | Linqing Liu, Huan Wang, Jimmy Lin, Richard Socher, Caiming Xiong |
| Abstract | In this paper, we explore the knowledge distillation approach under the multi-task learning setting. We distill the BERT model refined by multi-task learning on seven datasets of the GLUE benchmark into a bidirectional LSTM with attention mechanism. Unlike other BERT distillation methods which specifically designed for Transformer-based architectures, we provide a general learning framework. Our approach is model agnostic and can be easily applied on different future teacher models. Compared to a strong, similarly BiLSTM-based approach, we achieve better quality under the same computational constraints. Compared to the present state of the art, we reach comparable results with much faster inference speed. |
| Tasks | Multi-Task Learning |
| Published | 2019-11-09 |
| URL | https://arxiv.org/abs/1911.03588v1 |
| https://arxiv.org/pdf/1911.03588v1.pdf | |
| PWC | https://paperswithcode.com/paper/attentive-student-meets-multi-task-teacher |
| Repo | |
| Framework | |
Learning Generalized Models by Interrogating Black-Box Autonomous Agents
| Title | Learning Generalized Models by Interrogating Black-Box Autonomous Agents |
| Authors | Pulkit Verma, Siddharth Srivastava |
| Abstract | This paper develops a new approach for estimating a relational model of a non-stationary black-box autonomous agent that can plan and act. In this approach, the user may ask an autonomous agent a series of questions, which the agent answers truthfully. Our main contribution is an algorithm that generates an interrogation policy in the form of a contingent sequence of questions to be posed to the agent. Answers to these questions are used to derive a minimal, functionally indistinguishable class of agent models. This approach requires a minimal query-answering capability from the agent. Empirical evaluation of our approach shows that despite the intractable space of possible models, our approach allows correct and scalable estimation of relational STRIPS-like agent models for a class of black-box autonomous agents. |
| Tasks | |
| Published | 2019-12-29 |
| URL | https://arxiv.org/abs/1912.12613v2 |
| https://arxiv.org/pdf/1912.12613v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-generalized-models-by-interrogating |
| Repo | |
| Framework | |
A Framework for On-line Learning of Underwater Vehicles Dynamic Models
| Title | A Framework for On-line Learning of Underwater Vehicles Dynamic Models |
| Authors | Bilal Wehbe, Marc Hildebrandt, Frank Kirchner |
| Abstract | Learning the dynamics of robots from data can help achieve more accurate tracking controllers, or aid their navigation algorithms. However, when the actual dynamics of the robots change due to external conditions, on-line adaptation of their models is required to maintain high fidelity performance. In this work, a framework for on-line learning of robot dynamics is developed to adapt to such changes. The proposed framework employs an incremental support vector regression method to learn the model sequentially from data streams. In combination with the incremental learning, strategies for including and forgetting data are developed to obtain better generalization over the whole state space. The framework is tested in simulation and real experimental scenarios demonstrating its adaptation capabilities to changes in the robot’s dynamics. |
| Tasks | |
| Published | 2019-03-13 |
| URL | http://arxiv.org/abs/1903.05355v1 |
| http://arxiv.org/pdf/1903.05355v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-framework-for-on-line-learning-of |
| Repo | |
| Framework | |
The Impact of Time on Hashtag Reuse in Twitter: A Cognitive-Inspired Hashtag Recommendation Approach
| Title | The Impact of Time on Hashtag Reuse in Twitter: A Cognitive-Inspired Hashtag Recommendation Approach |
| Authors | Elisabeth Lex, Dominik Kowald |
| Abstract | In our work [KPL17], we study temporal usage patterns of Twitter hashtags, and we use the Base-Level Learning (BLL) equation from the cognitive architecture ACT-R [An04] to model how a person reuses her own, individual hashtags as well as hashtags from her social network. The BLL equation accounts for the time-dependent decay of item exposure in human memory. According to BLL, the usefulness of a piece of information (e.g., a hashtag) is defined by how frequently and how recently it was used in the past, following a time-dependent decay that is best modeled with a power-law distribution. We used the BLL equation in our previous work to recommend tags in social bookmarking systems [KL16]. Here [KPL17], we adopt the BLL equation to model temporal reuse patterns of individual (i.e., reusing own hashtags) and social hashtags (i.e., reusing hashtags, which has been previously used by a followee) and to build a cognitive-inspired hashtag recommendation algorithm. We demonstrate the efficacy of our approach in two empirical social networks crawled from Twitter, i.e., CompSci and Random (for details about the datasets, see [KPL17]). Our results show that our approach can outperform current state-of-the-art hashtag recommendation approaches. |
| Tasks | |
| Published | 2019-08-02 |
| URL | https://arxiv.org/abs/1908.00977v1 |
| https://arxiv.org/pdf/1908.00977v1.pdf | |
| PWC | https://paperswithcode.com/paper/the-impact-of-time-on-hashtag-reuse-in |
| Repo | |
| Framework | |
Topological Data Analysis for Arrhythmia Detection through Modular Neural Networks
| Title | Topological Data Analysis for Arrhythmia Detection through Modular Neural Networks |
| Authors | Meryll Dindin, Yuhei Umeda, Frederic Chazal |
| Abstract | This paper presents an innovative and generic deep learning approach to monitor heart conditions from ECG signals.We focus our attention on both the detection and classification of abnormal heartbeats, known as arrhythmia. We strongly insist on generalization throughout the construction of a deep-learning model that turns out to be effective for new unseen patient. The novelty of our approach relies on the use of topological data analysis as basis of our multichannel architecture, to diminish the bias due to individual differences. We show that our structure reaches the performances of the state-of-the-art methods regarding arrhythmia detection and classification. |
| Tasks | Arrhythmia Detection, Topological Data Analysis |
| Published | 2019-06-13 |
| URL | https://arxiv.org/abs/1906.05795v1 |
| https://arxiv.org/pdf/1906.05795v1.pdf | |
| PWC | https://paperswithcode.com/paper/topological-data-analysis-for-arrhythmia |
| Repo | |
| Framework | |
