Paper Group ANR 337
Lexical Sememe Prediction using Dictionary Definitions by Capturing Local Semantic Correspondence. Antifragility Predicts the Robustness and Evolvability of Biological Networks through Multi-class Classification with a Convolutional Neural Network. Machine learning based co-creative design framework. Siamese Neural Networks for EEG-based Brain-comp …
Lexical Sememe Prediction using Dictionary Definitions by Capturing Local Semantic Correspondence
| Title | Lexical Sememe Prediction using Dictionary Definitions by Capturing Local Semantic Correspondence |
| Authors | Jiaju Du, Fanchao Qi, Maosong Sun, Zhiyuan Liu |
| Abstract | Sememes, defined as the minimum semantic units of human languages in linguistics, have been proven useful in many NLP tasks. Since manual construction and update of sememe knowledge bases (KBs) are costly, the task of automatic sememe prediction has been proposed to assist sememe annotation. In this paper, we explore the approach of applying dictionary definitions to predicting sememes for unannotated words. We find that sememes of each word are usually semantically matched to different words in its dictionary definition, and we name this matching relationship local semantic correspondence. Accordingly, we propose a Sememe Correspondence Pooling (SCorP) model, which is able to capture this kind of matching to predict sememes. We evaluate our model and baseline methods on a famous sememe KB HowNet and find that our model achieves state-of-the-art performance. Moreover, further quantitative analysis shows that our model can properly learn the local semantic correspondence between sememes and words in dictionary definitions, which explains the effectiveness of our model. The source codes of this paper can be obtained from https://github.com/thunlp/scorp. |
| Tasks | |
| Published | 2020-01-16 |
| URL | https://arxiv.org/abs/2001.05954v1 |
| https://arxiv.org/pdf/2001.05954v1.pdf | |
| PWC | https://paperswithcode.com/paper/lexical-sememe-prediction-using-dictionary |
| Repo | |
| Framework | |
Antifragility Predicts the Robustness and Evolvability of Biological Networks through Multi-class Classification with a Convolutional Neural Network
| Title | Antifragility Predicts the Robustness and Evolvability of Biological Networks through Multi-class Classification with a Convolutional Neural Network |
| Authors | Hyobin Kim, Stalin Muñoz, Pamela Osuna, Carlos Gershenson |
| Abstract | Robustness and evolvability are essential properties to the evolution of biological networks. To determine if a biological network is robust and/or evolvable, the comparison of its functions before and after mutations is required. However, it has an increasing computational cost as network size grows. Here we aim to develop a predictor to estimate the robustness and evolvability of biological networks without an explicit comparison of functions. We measure antifragility in Boolean network models of biological systems and use this as the predictor. Antifragility is a property to improve the capability of a system through external perturbations. By means of the differences of antifragility between the original and mutated biological networks, we train a convolutional neural network (CNN) and test it to classify the properties of robustness and evolvability. We found that our CNN model successfully classified the properties. Thus, we conclude that our antifragility measure can be used as a significant predictor of the robustness and evolvability of biological networks. |
| Tasks | |
| Published | 2020-02-04 |
| URL | https://arxiv.org/abs/2002.01571v1 |
| https://arxiv.org/pdf/2002.01571v1.pdf | |
| PWC | https://paperswithcode.com/paper/antifragility-predicts-the-robustness-and |
| Repo | |
| Framework | |
Machine learning based co-creative design framework
| Title | Machine learning based co-creative design framework |
| Authors | Brian Quanz, Wei Sun, Ajay Deshpande, Dhruv Shah, Jae-eun Park |
| Abstract | We propose a flexible, co-creative framework bringing together multiple machine learning techniques to assist human users to efficiently produce effective creative designs. We demonstrate its potential with a perfume bottle design case study, including human evaluation and quantitative and qualitative analyses. |
| Tasks | |
| Published | 2020-01-23 |
| URL | https://arxiv.org/abs/2001.08791v1 |
| https://arxiv.org/pdf/2001.08791v1.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-based-co-creative-design |
| Repo | |
| Framework | |
Siamese Neural Networks for EEG-based Brain-computer Interfaces
| Title | Siamese Neural Networks for EEG-based Brain-computer Interfaces |
| Authors | Soroosh Shahtalebi, Amir Asif, Arash Mohammadi |
| Abstract | Motivated by the inconceivable capability of the human brain in simultaneously processing multi-modal signals and its real-time feedback to the outer world events, there has been a surge of interest in establishing a communication bridge between the human brain and a computer, which are referred to as Brain-computer Interfaces (BCI). To this aim, monitoring the electrical activity of brain through Electroencephalogram (EEG) has emerged as the prime choice for BCI systems. To discover the underlying and specific features of brain signals for different mental tasks, a considerable number of research works are developed based on statistical and data-driven techniques. However, a major bottleneck in the development of practical and commercial BCI systems is their limited performance when the number of mental tasks for classification is increased. In this work, we propose a new EEG processing and feature extraction paradigm based on Siamese neural networks, which can be conveniently merged and scaled up for multi-class problems. The idea of Siamese networks is to train a double-input neural network based on a contrastive loss-function, which provides the capability of verifying if two input EEG trials are from the same class or not. In this work, a Siamese architecture, which is developed based on Convolutional Neural Networks (CNN) and provides a binary output on the similarity of two inputs, is combined with OVR and OVO techniques to scale up for multi-class problems. The efficacy of this architecture is evaluated on a 4-class Motor Imagery (MI) dataset from BCI Competition IV-2a and the results suggest a promising performance compared to its counterparts. |
| Tasks | EEG |
| Published | 2020-02-03 |
| URL | https://arxiv.org/abs/2002.00904v1 |
| https://arxiv.org/pdf/2002.00904v1.pdf | |
| PWC | https://paperswithcode.com/paper/siamese-neural-networks-for-eeg-based-brain |
| Repo | |
| Framework | |
Capturing Evolution in Word Usage: Just Add More Clusters?
| Title | Capturing Evolution in Word Usage: Just Add More Clusters? |
| Authors | Matej Martinc, Syrielle Montariol, Elaine Zosa, Lidia Pivovarova |
| Abstract | The way the words are used evolves through time, mirroring cultural or technological evolution of society. Semantic change detection is the task of detecting and analysing word evolution in textual data, even in short periods of time. In this paper we focus on a new set of methods relying on contextualised embeddings, a type of semantic modelling that revolutionised the NLP field recently. We leverage the ability of the transformer-based BERT model to generate contextualised embeddings capable of detecting semantic change of words across time. Several approaches are compared in a common setting in order to establish strengths and weaknesses for each of them. We also propose several ideas for improvements, managing to drastically improve the performance of existing approaches. |
| Tasks | |
| Published | 2020-01-18 |
| URL | https://arxiv.org/abs/2001.06629v2 |
| https://arxiv.org/pdf/2001.06629v2.pdf | |
| PWC | https://paperswithcode.com/paper/capturing-evolution-in-word-usage-just-add |
| Repo | |
| Framework | |
stream-learn – open-source Python library for difficult data stream batch analysis
| Title | stream-learn – open-source Python library for difficult data stream batch analysis |
| Authors | Paweł Ksieniewicz, Paweł Zyblewski |
| Abstract | stream-learn is a Python package compatible with scikit-learn and developed for the drifting and imbalanced data stream analysis. Its main component is a stream generator, which allows to produce a synthetic data stream that may incorporate each of the three main concept drift types (i.e. sudden, gradual and incremental drift) in their recurring or non-recurring versions. The package allows conducting experiments following established evaluation methodologies (i.e. Test-Then-Train and Prequential). In addition, estimators adapted for data stream classification have been implemented, including both simple classifiers and state-of-art chunk-based and online classifier ensembles. To improve computational efficiency, package utilises its own implementations of prediction metrics for imbalanced binary classification tasks. |
| Tasks | |
| Published | 2020-01-29 |
| URL | https://arxiv.org/abs/2001.11077v1 |
| https://arxiv.org/pdf/2001.11077v1.pdf | |
| PWC | https://paperswithcode.com/paper/stream-learn-open-source-python-library-for |
| Repo | |
| Framework | |
Variational Hyper RNN for Sequence Modeling
| Title | Variational Hyper RNN for Sequence Modeling |
| Authors | Ruizhi Deng, Yanshuai Cao, Bo Chang, Leonid Sigal, Greg Mori, Marcus A. Brubaker |
| Abstract | In this work, we propose a novel probabilistic sequence model that excels at capturing high variability in time series data, both across sequences and within an individual sequence. Our method uses temporal latent variables to capture information about the underlying data pattern and dynamically decodes the latent information into modifications of weights of the base decoder and recurrent model. The efficacy of the proposed method is demonstrated on a range of synthetic and real-world sequential data that exhibit large scale variations, regime shifts, and complex dynamics. |
| Tasks | Time Series |
| Published | 2020-02-24 |
| URL | https://arxiv.org/abs/2002.10501v1 |
| https://arxiv.org/pdf/2002.10501v1.pdf | |
| PWC | https://paperswithcode.com/paper/variational-hyper-rnn-for-sequence-modeling-1 |
| Repo | |
| Framework | |
Adjust Planning Strategies to Accommodate Reinforcement Learning Agents
| Title | Adjust Planning Strategies to Accommodate Reinforcement Learning Agents |
| Authors | Xuerun Chen |
| Abstract | In agent control issues, the idea of combining reinforcement learning and planning has attracted much attention. Two methods focus on micro and macro action respectively. Their advantages would show together if there is a good cooperation between them. An essential for the cooperation is to find an appropriate boundary, assigning different functions to each method. Such boundary could be represented by parameters in a planning algorithm. In this paper, we create an optimization strategy for planning parameters, through analysis to the connection of reaction and planning; we also create a non-gradient method for accelerating the optimization. The whole algorithm can find a satisfactory setting of planning parameters, making full use of reaction capability of specific agents. |
| Tasks | |
| Published | 2020-03-19 |
| URL | https://arxiv.org/abs/2003.08554v1 |
| https://arxiv.org/pdf/2003.08554v1.pdf | |
| PWC | https://paperswithcode.com/paper/adjust-planning-strategies-to-accommodate |
| Repo | |
| Framework | |
Prophet: Proactive Candidate-Selection for Federated Learning by Predicting the Qualities of Training and Reporting Phases
| Title | Prophet: Proactive Candidate-Selection for Federated Learning by Predicting the Qualities of Training and Reporting Phases |
| Authors | Huawei Huang, Kangying Lin, Song Guo, Pan Zhou, Zibin Zheng |
| Abstract | Federated Learning (FL) is viewed as a promising technique for future distributed machine learning. It permits a large number of mobile devices participating in the training of a global model collaboratively without having to expose their local private data. Although the challenge of the network connection will be much relieved in 5G/B5G era, the training latency is still an obstacle preventing FL from being largely adopted. One of the most fundamental problems that leads to large training latency is the bad candidate-selection of FL participants. To the best of our knowledge, the existing candidate-selection algorithms belong to the reactive manner. Under such reactive selection, the FL parameter server only knows the currently-observed resources of all candidates. In the dynamic FL environment, the mobile devices selected by the reactive candidate-selection algorithms very possibly fail to complete the training and reporting phases of FL. To this end, we study the proactive candidate-selection for FL in this paper. We first let each candidate device locally predict the qualities of both its training and reporting phases using the LSTM network. Then, the proposed candidate-selection algorithm is implemented by the Deep Reinforcement Learning (DRL) framework, which can adapt to the dynamically varying factors in the metropolitan edge computing environment. Finally, the real-world trace-driven experiments prove that the proposed proactive approach outperforms the existing reactive algorithms with respect to the ratio of valid participants and the test accuracy of the aggregated global FL model. |
| Tasks | |
| Published | 2020-02-03 |
| URL | https://arxiv.org/abs/2002.00577v1 |
| https://arxiv.org/pdf/2002.00577v1.pdf | |
| PWC | https://paperswithcode.com/paper/prophet-proactive-candidate-selection-for |
| Repo | |
| Framework | |
Dynamic Spatiotemporal Graph Neural Network with Tensor Network
| Title | Dynamic Spatiotemporal Graph Neural Network with Tensor Network |
| Authors | Chengcheng Jia, Bo Wu, Xiao-Ping Zhang |
| Abstract | Dynamic spatial graph construction is a challenge in graph neural network (GNN) for time series data problems. Although some adaptive graphs are conceivable, only a 2D graph is embedded in the network to reflect the current spatial relation, regardless of all the previous situations. In this work, we generate a spatial tensor graph (STG) to collect all the dynamic spatial relations, as well as a temporal tensor graph (TTG) to find the latent pattern along time at each node. These two tensor graphs share the same nodes and edges, which leading us to explore their entangled correlations by Projected Entangled Pair States (PEPS) to optimize the two graphs. We experimentally compare the accuracy and time costing with the state-of-the-art GNN based methods on the public traffic datasets. |
| Tasks | graph construction, Time Series |
| Published | 2020-03-12 |
| URL | https://arxiv.org/abs/2003.08729v1 |
| https://arxiv.org/pdf/2003.08729v1.pdf | |
| PWC | https://paperswithcode.com/paper/dynamic-spatiotemporal-graph-neural-network |
| Repo | |
| Framework | |
Predicting Yield Performance of Parents in Plant Breeding: A Neural Collaborative Filtering Approach
| Title | Predicting Yield Performance of Parents in Plant Breeding: A Neural Collaborative Filtering Approach |
| Authors | Saeed Khaki, Zahra Khalilzadeh, Lizhi Wang |
| Abstract | Experimental corn hybrids are created in plant breeding programs by crossing two parents, so-called inbred and tester, together. Identification of best parent combinations for crossing is challenging since the total number of possible cross combinations of parents is large and it is impractical to test all possible cross combinations due to limited resources of time and budget. In the 2020 Syngenta Crop Challenge, Syngenta released several large datasets that recorded the historical yield performances of around 4% of total cross combinations of 593 inbreds with 496 testers which were planted in 280 locations between 2016 and 2018 and asked participants to predict the yield performance of cross combinations of inbreds and testers that have not been planted based on the historical yield data collected from crossing other inbreds and testers. In this paper, we present a collaborative filtering method which is an ensemble of matrix factorization method and neural networks to solve this problem. Our computational results suggested that the proposed model significantly outperformed other models such as LASSO, random forest (RF), and neural networks. Presented method and results were produced within the 2020 Syngenta Crop Challenge. |
| Tasks | |
| Published | 2020-01-27 |
| URL | https://arxiv.org/abs/2001.09902v1 |
| https://arxiv.org/pdf/2001.09902v1.pdf | |
| PWC | https://paperswithcode.com/paper/predicting-yield-performance-of-parents-in |
| Repo | |
| Framework | |
End-to-End Entity Classification on Multimodal Knowledge Graphs
| Title | End-to-End Entity Classification on Multimodal Knowledge Graphs |
| Authors | W. X. Wilcke, P. Bloem, V. de Boer, R. H. van t Veer, F. A. H. van Harmelen |
| Abstract | End-to-end multimodal learning on knowledge graphs has been left largely unaddressed. Instead, most end-to-end models such as message passing networks learn solely from the relational information encoded in graphs’ structure: raw values, or literals, are either omitted completely or are stripped from their values and treated as regular nodes. In either case we lose potentially relevant information which could have otherwise been exploited by our learning methods. To avoid this, we must treat literals and non-literals as separate cases. We must also address each modality separately and accordingly: numbers, texts, images, geometries, et cetera. We propose a multimodal message passing network which not only learns end-to-end from the structure of graphs, but also from their possibly divers set of multimodal node features. Our model uses dedicated (neural) encoders to naturally learn embeddings for node features belonging to five different types of modalities, including images and geometries, which are projected into a joint representation space together with their relational information. We demonstrate our model on a node classification task, and evaluate the effect that each modality has on the overall performance. Our result supports our hypothesis that including information from multiple modalities can help our models obtain a better overall performance. |
| Tasks | Knowledge Graphs, Node Classification |
| Published | 2020-03-25 |
| URL | https://arxiv.org/abs/2003.12383v1 |
| https://arxiv.org/pdf/2003.12383v1.pdf | |
| PWC | https://paperswithcode.com/paper/end-to-end-entity-classification-on |
| Repo | |
| Framework | |
Manipulating Reinforcement Learning: Poisoning Attacks on Cost Signals
| Title | Manipulating Reinforcement Learning: Poisoning Attacks on Cost Signals |
| Authors | Yunhan Huang, Quanyan Zhu |
| Abstract | This chapter studies emerging cyber-attacks on reinforcement learning (RL) and introduces a quantitative approach to analyze the vulnerabilities of RL. Focusing on adversarial manipulation on the cost signals, we analyze the performance degradation of TD($\lambda$) and $Q$-learning algorithms under the manipulation. For TD($\lambda$), the approximation learned from the manipulated costs has an approximation error bound proportional to the magnitude of the attack. The effect of the adversarial attacks on the bound does not depend on the choice of $\lambda$. In $Q$-learning, we show that $Q$-learning algorithms converge under stealthy attacks and bounded falsifications on cost signals. We characterize the relation between the falsified cost and the $Q$-factors as well as the policy learned by the learning agent which provides fundamental limits for feasible offensive and defensive moves. We propose a robust region in terms of the cost within which the adversary can never achieve the targeted policy. We provide conditions on the falsified cost which can mislead the agent to learn an adversary’s favored policy. A case study of TD($\lambda$) learning is provided to corroborate the results. |
| Tasks | Q-Learning |
| Published | 2020-02-07 |
| URL | https://arxiv.org/abs/2002.03827v1 |
| https://arxiv.org/pdf/2002.03827v1.pdf | |
| PWC | https://paperswithcode.com/paper/manipulating-reinforcement-learning-poisoning |
| Repo | |
| Framework | |
Incorporating Visual Semantics into Sentence Representations within a Grounded Space
| Title | Incorporating Visual Semantics into Sentence Representations within a Grounded Space |
| Authors | Patrick Bordes, Eloi Zablocki, Laure Soulier, Benjamin Piwowarski, Patrick Gallinari |
| Abstract | Language grounding is an active field aiming at enriching textual representations with visual information. Generally, textual and visual elements are embedded in the same representation space, which implicitly assumes a one-to-one correspondence between modalities. This hypothesis does not hold when representing words, and becomes problematic when used to learn sentence representations — the focus of this paper — as a visual scene can be described by a wide variety of sentences. To overcome this limitation, we propose to transfer visual information to textual representations by learning an intermediate representation space: the grounded space. We further propose two new complementary objectives ensuring that (1) sentences associated with the same visual content are close in the grounded space and (2) similarities between related elements are preserved across modalities. We show that this model outperforms the previous state-of-the-art on classification and semantic relatedness tasks. |
| Tasks | |
| Published | 2020-02-07 |
| URL | https://arxiv.org/abs/2002.02734v1 |
| https://arxiv.org/pdf/2002.02734v1.pdf | |
| PWC | https://paperswithcode.com/paper/incorporating-visual-semantics-into-sentence-1 |
| Repo | |
| Framework | |
Finite-Time Analysis of Asynchronous Stochastic Approximation and $Q$-Learning
| Title | Finite-Time Analysis of Asynchronous Stochastic Approximation and $Q$-Learning |
| Authors | Guannan Qu, Adam Wierman |
| Abstract | We consider a general asynchronous Stochastic Approximation (SA) scheme featuring a weighted infinity-norm contractive operator, and prove a bound on its finite-time convergence rate on a single trajectory. Additionally, we specialize the result to asynchronous $Q$-learning. The resulting bound matches the sharpest available bound for synchronous $Q$-learning, and improves over previous known bounds for asynchronous $Q$-learning. |
| Tasks | Q-Learning |
| Published | 2020-02-01 |
| URL | https://arxiv.org/abs/2002.00260v1 |
| https://arxiv.org/pdf/2002.00260v1.pdf | |
| PWC | https://paperswithcode.com/paper/finite-time-analysis-of-asynchronous |
| Repo | |
| Framework | |
