Pub Date : 2022-12-21DOI: 10.48550/arXiv.2212.10847
Victor Guyomard, Franccoise Fessant, Thomas Guyet, Tassadit Bouadi, A. Termier
Counterfactual explanation is a common class of methods to make local explanations of machine learning decisions. For a given instance, these methods aim to find the smallest modification of feature values that changes the predicted decision made by a machine learning model. One of the challenges of counterfactual explanation is the efficient generation of realistic counterfactuals. To address this challenge, we propose VCNet-Variational Counter Net-a model architecture that combines a predictor and a counterfactual generator that are jointly trained, for regression or classification tasks. VCNet is able to both generate predictions, and to generate counterfactual explanations without having to solve another minimisation problem. Our contribution is the generation of counterfactuals that are close to the distribution of the predicted class. This is done by learning a variational autoencoder conditionally to the output of the predictor in a join-training fashion. We present an empirical evaluation on tabular datasets and across several interpretability metrics. The results are competitive with the state-of-the-art method.
{"title":"VCNet: A self-explaining model for realistic counterfactual generation","authors":"Victor Guyomard, Franccoise Fessant, Thomas Guyet, Tassadit Bouadi, A. Termier","doi":"10.48550/arXiv.2212.10847","DOIUrl":"https://doi.org/10.48550/arXiv.2212.10847","url":null,"abstract":"Counterfactual explanation is a common class of methods to make local explanations of machine learning decisions. For a given instance, these methods aim to find the smallest modification of feature values that changes the predicted decision made by a machine learning model. One of the challenges of counterfactual explanation is the efficient generation of realistic counterfactuals. To address this challenge, we propose VCNet-Variational Counter Net-a model architecture that combines a predictor and a counterfactual generator that are jointly trained, for regression or classification tasks. VCNet is able to both generate predictions, and to generate counterfactual explanations without having to solve another minimisation problem. Our contribution is the generation of counterfactuals that are close to the distribution of the predicted class. This is done by learning a variational autoencoder conditionally to the output of the predictor in a join-training fashion. We present an empirical evaluation on tabular datasets and across several interpretability metrics. The results are competitive with the state-of-the-art method.","PeriodicalId":74091,"journal":{"name":"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85573375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-14DOI: 10.48550/arXiv.2212.07524
Nam-Phuong Tran, The-Anh Ta, Long Tran-Thanh
Symmetry arises in many optimization and decision-making problems, and has attracted considerable attention from the optimization community: By utilizing the existence of such symmetries, the process of searching for optimal solutions can be improved significantly. Despite its success in (offline) optimization, the utilization of symmetries has not been well examined within the online optimization settings, especially in the bandit literature. As such, in this paper we study the invariant Lipschitz bandit setting, a subclass of the Lipschitz bandits where the reward function and the set of arms are preserved under a group of transformations. We introduce an algorithm named texttt{UniformMesh-N}, which naturally integrates side observations using group orbits into the texttt{UniformMesh} algorithm (cite{Kleinberg2005_UniformMesh}), which uniformly discretizes the set of arms. Using the side-observation approach, we prove an improved regret upper bound, which depends on the cardinality of the group, given that the group is finite. We also prove a matching regret's lower bound for the invariant Lipschitz bandit class (up to logarithmic factors). We hope that our work will ignite further investigation of symmetry in bandit theory and sequential decision-making theory in general.
{"title":"Invariant Lipschitz Bandits: A Side Observation Approach","authors":"Nam-Phuong Tran, The-Anh Ta, Long Tran-Thanh","doi":"10.48550/arXiv.2212.07524","DOIUrl":"https://doi.org/10.48550/arXiv.2212.07524","url":null,"abstract":"Symmetry arises in many optimization and decision-making problems, and has attracted considerable attention from the optimization community: By utilizing the existence of such symmetries, the process of searching for optimal solutions can be improved significantly. Despite its success in (offline) optimization, the utilization of symmetries has not been well examined within the online optimization settings, especially in the bandit literature. As such, in this paper we study the invariant Lipschitz bandit setting, a subclass of the Lipschitz bandits where the reward function and the set of arms are preserved under a group of transformations. We introduce an algorithm named texttt{UniformMesh-N}, which naturally integrates side observations using group orbits into the texttt{UniformMesh} algorithm (cite{Kleinberg2005_UniformMesh}), which uniformly discretizes the set of arms. Using the side-observation approach, we prove an improved regret upper bound, which depends on the cardinality of the group, given that the group is finite. We also prove a matching regret's lower bound for the invariant Lipschitz bandit class (up to logarithmic factors). We hope that our work will ignite further investigation of symmetry in bandit theory and sequential decision-making theory in general.","PeriodicalId":74091,"journal":{"name":"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86701469","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-18DOI: 10.48550/arXiv.2211.11583
Srinivas Virinchi, Anoop Saladi, Abhirup Mondal
Related product recommendation (RPR) is pivotal to the success of any e-commerce service. In this paper, we deal with the problem of recommending related products i.e., given a query product, we would like to suggest top-k products that have high likelihood to be bought together with it. Our problem implicitly assumes asymmetry i.e., for a phone, we would like to recommend a suitable phone case, but for a phone case, it may not be apt to recommend a phone because customers typically would purchase a phone case only while owning a phone. We also do not limit ourselves to complementary or substitute product recommendation. For example, for a specific night wear t-shirt, we can suggest similar t-shirts as well as track pants. So, the notion of relatedness is subjective to the query product and dependent on customer preferences. Further, various factors such as product price, availability lead to presence of selection bias in the historical purchase data, that needs to be controlled for while training related product recommendations model. These challenges are orthogonal to each other deeming our problem nontrivial. To address these, we propose DAEMON, a novel Graph Neural Network (GNN) based framework for related product recommendation, wherein the problem is formulated as a node recommendation task on a directed product graph. In order to capture product asymmetry, we employ an asymmetric loss function and learn dual embeddings for each product, by appropriately aggregating features from its neighborhood. DAEMON leverages multi-modal data sources such as catalog metadata, browse behavioral logs to mitigate selection bias and generate recommendations for cold-start products. Extensive offline experiments show that DAEMON outperforms state-of-the-art baselines by 30-160% in terms of HitRate and MRR for the node recommendation task.
{"title":"Recommending Related Products Using Graph Neural Networks in Directed Graphs","authors":"Srinivas Virinchi, Anoop Saladi, Abhirup Mondal","doi":"10.48550/arXiv.2211.11583","DOIUrl":"https://doi.org/10.48550/arXiv.2211.11583","url":null,"abstract":"Related product recommendation (RPR) is pivotal to the success of any e-commerce service. In this paper, we deal with the problem of recommending related products i.e., given a query product, we would like to suggest top-k products that have high likelihood to be bought together with it. Our problem implicitly assumes asymmetry i.e., for a phone, we would like to recommend a suitable phone case, but for a phone case, it may not be apt to recommend a phone because customers typically would purchase a phone case only while owning a phone. We also do not limit ourselves to complementary or substitute product recommendation. For example, for a specific night wear t-shirt, we can suggest similar t-shirts as well as track pants. So, the notion of relatedness is subjective to the query product and dependent on customer preferences. Further, various factors such as product price, availability lead to presence of selection bias in the historical purchase data, that needs to be controlled for while training related product recommendations model. These challenges are orthogonal to each other deeming our problem nontrivial. To address these, we propose DAEMON, a novel Graph Neural Network (GNN) based framework for related product recommendation, wherein the problem is formulated as a node recommendation task on a directed product graph. In order to capture product asymmetry, we employ an asymmetric loss function and learn dual embeddings for each product, by appropriately aggregating features from its neighborhood. DAEMON leverages multi-modal data sources such as catalog metadata, browse behavioral logs to mitigate selection bias and generate recommendations for cold-start products. Extensive offline experiments show that DAEMON outperforms state-of-the-art baselines by 30-160% in terms of HitRate and MRR for the node recommendation task.","PeriodicalId":74091,"journal":{"name":"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76023368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Recent studies show that Graph Neural Networks(GNNs) are vulnerable and easily fooled by small perturbations, which has raised considerable concerns for adapting GNNs in various safety-critical applications. In this work, we focus on the emerging but critical attack, namely, Graph Injection Attack(GIA), in which the adversary poisons the graph by injecting fake nodes instead of modifying existing structures or node attributes. Inspired by findings that the adversarial attacks are related to the increased heterophily on perturbed graphs (the adversary tends to connect dissimilar nodes), we propose a general defense framework CHAGNN against GIA through cooperative homophilous augmentation of graph data and model. Specifically, the model generates pseudo-labels for unlabeled nodes in each round of training to reduce heterophilous edges of nodes with distinct labels. The cleaner graph is fed back to the model, producing more informative pseudo-labels. In such an iterative manner, model robustness is then promisingly enhanced. We present the theoretical analysis of the effect of homophilous augmentation and provide the guarantee of the proposal's validity. Experimental results empirically demonstrate the effectiveness of CHAGNN in comparison with recent state-of-the-art defense methods on diverse real-world datasets.
{"title":"Resisting Graph Adversarial Attack via Cooperative Homophilous Augmentation","authors":"Zhihao Zhu, Chenwang Wu, Mingyang Zhou, Hao Liao, DefuLian, Enhong Chen","doi":"10.48550/arXiv.2211.08068","DOIUrl":"https://doi.org/10.48550/arXiv.2211.08068","url":null,"abstract":"Recent studies show that Graph Neural Networks(GNNs) are vulnerable and easily fooled by small perturbations, which has raised considerable concerns for adapting GNNs in various safety-critical applications. In this work, we focus on the emerging but critical attack, namely, Graph Injection Attack(GIA), in which the adversary poisons the graph by injecting fake nodes instead of modifying existing structures or node attributes. Inspired by findings that the adversarial attacks are related to the increased heterophily on perturbed graphs (the adversary tends to connect dissimilar nodes), we propose a general defense framework CHAGNN against GIA through cooperative homophilous augmentation of graph data and model. Specifically, the model generates pseudo-labels for unlabeled nodes in each round of training to reduce heterophilous edges of nodes with distinct labels. The cleaner graph is fed back to the model, producing more informative pseudo-labels. In such an iterative manner, model robustness is then promisingly enhanced. We present the theoretical analysis of the effect of homophilous augmentation and provide the guarantee of the proposal's validity. Experimental results empirically demonstrate the effectiveness of CHAGNN in comparison with recent state-of-the-art defense methods on diverse real-world datasets.","PeriodicalId":74091,"journal":{"name":"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76998425","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-14DOI: 10.48550/arXiv.2211.07387
Steven Bilaj, Sofien Dhouib, S. Maghsudi
We consider the problem of contextual multi-armed bandits in the setting of hypothesis transfer learning. That is, we assume having access to a previously learned model on an unobserved set of contexts, and we leverage it in order to accelerate exploration on a new bandit problem. Our transfer strategy is based on a re-weighting scheme for which we show a reduction in the regret over the classic Linear UCB when transfer is desired, while recovering the classic regret rate when the two tasks are unrelated. We further extend this method to an arbitrary amount of source models, where the algorithm decides which model is preferred at each time step. Additionally we discuss an approach where a dynamic convex combination of source models is given in terms of a biased regularization term in the classic LinUCB algorithm. The algorithms and the theoretical analysis of our proposed methods substantiated by empirical evaluations on simulated and real-world data.
{"title":"Hypothesis Transfer in Bandits by Weighted Models","authors":"Steven Bilaj, Sofien Dhouib, S. Maghsudi","doi":"10.48550/arXiv.2211.07387","DOIUrl":"https://doi.org/10.48550/arXiv.2211.07387","url":null,"abstract":"We consider the problem of contextual multi-armed bandits in the setting of hypothesis transfer learning. That is, we assume having access to a previously learned model on an unobserved set of contexts, and we leverage it in order to accelerate exploration on a new bandit problem. Our transfer strategy is based on a re-weighting scheme for which we show a reduction in the regret over the classic Linear UCB when transfer is desired, while recovering the classic regret rate when the two tasks are unrelated. We further extend this method to an arbitrary amount of source models, where the algorithm decides which model is preferred at each time step. Additionally we discuss an approach where a dynamic convex combination of source models is given in terms of a biased regularization term in the classic LinUCB algorithm. The algorithms and the theoretical analysis of our proposed methods substantiated by empirical evaluations on simulated and real-world data.","PeriodicalId":74091,"journal":{"name":"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74754306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-11-07DOI: 10.48550/arXiv.2211.03248
Shu Yu Tew, D. Schmidt, E. Makalic
The horseshoe prior is known to possess many desirable properties for Bayesian estimation of sparse parameter vectors, yet its density function lacks an analytic form. As such, it is challenging to find a closed-form solution for the posterior mode. Conventional horseshoe estimators use the posterior mean to estimate the parameters, but these estimates are not sparse. We propose a novel expectation-maximisation (EM) procedure for computing the MAP estimates of the parameters in the case of the standard linear model. A particular strength of our approach is that the M-step depends only on the form of the prior and it is independent of the form of the likelihood. We introduce several simple modifications of this EM procedure that allow for straightforward extension to generalised linear models. In experiments performed on simulated and real data, our approach performs comparable, or superior to, state-of-the-art sparse estimation methods in terms of statistical performance and computational cost.
{"title":"Sparse Horseshoe Estimation via Expectation-Maximisation","authors":"Shu Yu Tew, D. Schmidt, E. Makalic","doi":"10.48550/arXiv.2211.03248","DOIUrl":"https://doi.org/10.48550/arXiv.2211.03248","url":null,"abstract":"The horseshoe prior is known to possess many desirable properties for Bayesian estimation of sparse parameter vectors, yet its density function lacks an analytic form. As such, it is challenging to find a closed-form solution for the posterior mode. Conventional horseshoe estimators use the posterior mean to estimate the parameters, but these estimates are not sparse. We propose a novel expectation-maximisation (EM) procedure for computing the MAP estimates of the parameters in the case of the standard linear model. A particular strength of our approach is that the M-step depends only on the form of the prior and it is independent of the form of the likelihood. We introduce several simple modifications of this EM procedure that allow for straightforward extension to generalised linear models. In experiments performed on simulated and real data, our approach performs comparable, or superior to, state-of-the-art sparse estimation methods in terms of statistical performance and computational cost.","PeriodicalId":74091,"journal":{"name":"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-11-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85672697","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-23DOI: 10.48550/arXiv.2210.12693
Chengyin Li, Zheng Dong, N. Fisher, D. Zhu
Electric Vehicle (EV) charging recommendation that both accommodates user preference and adapts to the ever-changing external environment arises as a cost-effective strategy to alleviate the range anxiety of private EV drivers. Previous studies focus on centralized strategies to achieve optimized resource allocation, particularly useful for privacy-indifferent taxi fleets and fixed-route public transits. However, private EV driver seeks a more personalized and resource-aware charging recommendation that is tailor-made to accommodate the user preference (when and where to charge) yet sufficiently adaptive to the spatiotemporal mismatch between charging supply and demand. Here we propose a novel Regularized Actor-Critic (RAC) charging recommendation approach that would allow each EV driver to strike an optimal balance between the user preference (historical charging pattern) and the external reward (driving distance and wait time). Experimental results on two real-world datasets demonstrate the unique features and superior performance of our approach to the competing methods.
{"title":"Coupling User Preference with External Rewards to Enable Driver-centered and Resource-aware EV Charging Recommendation","authors":"Chengyin Li, Zheng Dong, N. Fisher, D. Zhu","doi":"10.48550/arXiv.2210.12693","DOIUrl":"https://doi.org/10.48550/arXiv.2210.12693","url":null,"abstract":"Electric Vehicle (EV) charging recommendation that both accommodates user preference and adapts to the ever-changing external environment arises as a cost-effective strategy to alleviate the range anxiety of private EV drivers. Previous studies focus on centralized strategies to achieve optimized resource allocation, particularly useful for privacy-indifferent taxi fleets and fixed-route public transits. However, private EV driver seeks a more personalized and resource-aware charging recommendation that is tailor-made to accommodate the user preference (when and where to charge) yet sufficiently adaptive to the spatiotemporal mismatch between charging supply and demand. Here we propose a novel Regularized Actor-Critic (RAC) charging recommendation approach that would allow each EV driver to strike an optimal balance between the user preference (historical charging pattern) and the external reward (driving distance and wait time). Experimental results on two real-world datasets demonstrate the unique features and superior performance of our approach to the competing methods.","PeriodicalId":74091,"journal":{"name":"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75015747","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-10-21DOI: 10.48550/arXiv.2210.11950
Alexandre Hippert-Ferrer, Florent Bouchard, A. Mian, Titouan Vayer, A. Breloy
Graphical models and factor analysis are well-established tools in multivariate statistics. While these models can be both linked to structures exhibited by covariance and precision matrices, they are generally not jointly leveraged within graph learning processes. This paper therefore addresses this issue by proposing a flexible algorithmic framework for graph learning under low-rank structural constraints on the covariance matrix. The problem is expressed as penalized maximum likelihood estimation of an elliptical distribution (a generalization of Gaussian graphical models to possibly heavy-tailed distributions), where the covariance matrix is optionally constrained to be structured as low-rank plus diagonal (low-rank factor model). The resolution of this class of problems is then tackled with Riemannian optimization, where we leverage geometries of positive definite matrices and positive semi-definite matrices of fixed rank that are well suited to elliptical models. Numerical experiments on real-world data sets illustrate the effectiveness of the proposed approach.
{"title":"Learning Graphical Factor Models with Riemannian Optimization","authors":"Alexandre Hippert-Ferrer, Florent Bouchard, A. Mian, Titouan Vayer, A. Breloy","doi":"10.48550/arXiv.2210.11950","DOIUrl":"https://doi.org/10.48550/arXiv.2210.11950","url":null,"abstract":"Graphical models and factor analysis are well-established tools in multivariate statistics. While these models can be both linked to structures exhibited by covariance and precision matrices, they are generally not jointly leveraged within graph learning processes. This paper therefore addresses this issue by proposing a flexible algorithmic framework for graph learning under low-rank structural constraints on the covariance matrix. The problem is expressed as penalized maximum likelihood estimation of an elliptical distribution (a generalization of Gaussian graphical models to possibly heavy-tailed distributions), where the covariance matrix is optionally constrained to be structured as low-rank plus diagonal (low-rank factor model). The resolution of this class of problems is then tackled with Riemannian optimization, where we leverage geometries of positive definite matrices and positive semi-definite matrices of fixed rank that are well suited to elliptical models. Numerical experiments on real-world data sets illustrate the effectiveness of the proposed approach.","PeriodicalId":74091,"journal":{"name":"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83470382","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Volume prediction is one of the fundamental objectives in the Fintech area, which is helpful for many downstream tasks, e.g., algorithmic trading. Previous methods mostly learn a universal model for different stocks. However, this kind of practice omits the specific characteristics of individual stocks by applying the same set of parameters for different stocks. On the other hand, learning different models for each stock would face data sparsity or cold start problems for many stocks with small capitalization. To take advantage of the data scale and the various characteristics of individual stocks, we propose a dual-process meta-learning method that treats the prediction of each stock as one task under the meta-learning framework. Our method can model the common pattern behind different stocks with a meta-learner, while modeling the specific pattern for each stock across time spans with stock-dependent parameters. Furthermore, we propose to mine the pattern of each stock in the form of a latent variable which is then used for learning the parameters for the prediction module. This makes the prediction procedure aware of the data pattern. Extensive experiments on volume predictions show that our method can improve the performance of various baseline models. Further analyses testify the effectiveness of our proposed meta-learning framework.
{"title":"Stock Trading Volume Prediction with Dual-Process Meta-Learning","authors":"Ruibo Chen, Wei Li, Zhiyuan Zhang, Ruihan Bao, Keiko Harimoto, Xu Sun","doi":"10.48550/arXiv.2211.01762","DOIUrl":"https://doi.org/10.48550/arXiv.2211.01762","url":null,"abstract":"Volume prediction is one of the fundamental objectives in the Fintech area, which is helpful for many downstream tasks, e.g., algorithmic trading. Previous methods mostly learn a universal model for different stocks. However, this kind of practice omits the specific characteristics of individual stocks by applying the same set of parameters for different stocks. On the other hand, learning different models for each stock would face data sparsity or cold start problems for many stocks with small capitalization. To take advantage of the data scale and the various characteristics of individual stocks, we propose a dual-process meta-learning method that treats the prediction of each stock as one task under the meta-learning framework. Our method can model the common pattern behind different stocks with a meta-learner, while modeling the specific pattern for each stock across time spans with stock-dependent parameters. Furthermore, we propose to mine the pattern of each stock in the form of a latent variable which is then used for learning the parameters for the prediction module. This makes the prediction procedure aware of the data pattern. Extensive experiments on volume predictions show that our method can improve the performance of various baseline models. Further analyses testify the effectiveness of our proposed meta-learning framework.","PeriodicalId":74091,"journal":{"name":"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-10-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82397435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-09-30DOI: 10.48550/arXiv.2209.15452
Y. Okawa, Tomotake Sasaki, H. Yanami, T. Namerikawa
Recent rapid developments in reinforcement learning algorithms have been giving us novel possibilities in many fields. However, due to their exploring property, we have to take the risk into consideration when we apply those algorithms to safety-critical problems especially in real environments. In this study, we deal with a safe exploration problem in reinforcement learning under the existence of disturbance. We define the safety during learning as satisfaction of the constraint conditions explicitly defined in terms of the state and propose a safe exploration method that uses partial prior knowledge of a controlled object and disturbance. The proposed method assures the satisfaction of the explicit state constraints with a pre-specified probability even if the controlled object is exposed to a stochastic disturbance following a normal distribution. As theoretical results, we introduce sufficient conditions to construct conservative inputs not containing an exploring aspect used in the proposed method and prove that the safety in the above explained sense is guaranteed with the proposed method. Furthermore, we illustrate the validity and effectiveness of the proposed method through numerical simulations of an inverted pendulum and a four-bar parallel link robot manipulator.
{"title":"Safe Exploration Method for Reinforcement Learning under Existence of Disturbance","authors":"Y. Okawa, Tomotake Sasaki, H. Yanami, T. Namerikawa","doi":"10.48550/arXiv.2209.15452","DOIUrl":"https://doi.org/10.48550/arXiv.2209.15452","url":null,"abstract":"Recent rapid developments in reinforcement learning algorithms have been giving us novel possibilities in many fields. However, due to their exploring property, we have to take the risk into consideration when we apply those algorithms to safety-critical problems especially in real environments. In this study, we deal with a safe exploration problem in reinforcement learning under the existence of disturbance. We define the safety during learning as satisfaction of the constraint conditions explicitly defined in terms of the state and propose a safe exploration method that uses partial prior knowledge of a controlled object and disturbance. The proposed method assures the satisfaction of the explicit state constraints with a pre-specified probability even if the controlled object is exposed to a stochastic disturbance following a normal distribution. As theoretical results, we introduce sufficient conditions to construct conservative inputs not containing an exploring aspect used in the proposed method and prove that the safety in the above explained sense is guaranteed with the proposed method. Furthermore, we illustrate the validity and effectiveness of the proposed method through numerical simulations of an inverted pendulum and a four-bar parallel link robot manipulator.","PeriodicalId":74091,"journal":{"name":"Machine learning and knowledge discovery in databases : European Conference, ECML PKDD ... : proceedings. ECML PKDD (Conference)","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74702055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：