Mauajama Firdaus, Nidhi Thakur, Asif Ekbal
Multimodality in dialogue systems has opened up new frontiers for the creation of robust conversational agents. Any multimodal system aims at bridging the gap between language and vision by leveraging diverse and often complementary information from image, audio, and video, as well as text. For every task-oriented dialog system, different aspects of the product or service are crucial for satisfying the user’s demands. Based upon the aspect, the user decides upon selecting the product or service. The ability to generate responses with the specified aspects in a goal-oriented dialogue setup facilitates user satisfaction by fulfilling the user’s goals. Therefore, in our current work, we propose the task of aspect controlled response generation in a multimodal task-oriented dialog system.
Category: ACM Transactions on Intelligent Systems and Technology
Industrial Federated Topic Modeling
Di Jiang, Yongxin Tong, Yuanfeng Song, Xueyang Wu, Weiwei Zhao, Jinhua Peng, Rongzhong Lian, Qian Xu, Qiang Yang
Probabilistic topic modeling has been applied in a variety of industrial applications. Training a high-quality model usually requires a massive amount of data to provide comprehensive co-occurrence information for the model to learn. However, industrial data such as medical or financial records are often proprietary or sensitive, which precludes uploading to data centers. Hence, training topic models in industrial scenarios using conventional approaches faces a dilemma: A party (i.e., a company or institute) has to either tolerate data scarcity or sacrifice data privacy. In this article, we propose a framework named Industrial Federated Topic Modeling (iFTM), in which multiple parties collaboratively train a high-quality topic model by simultaneously alleviating data scarcity and maintaining immunity to privacy adversaries.
Probabilistic topic modeling has been applied in a variety of industrial applications. Training a high-quality model usually requires a massive amount of data to provide comprehensive co-occurrence information for the model to learn. However, industrial data such as medical or financial records are often proprietary or sensitive, which precludes uploading to data centers. Hence, training topic models in industrial scenarios using conventional approaches faces a dilemma: A party (i.e., a company or institute) has to either tolerate data scarcity or sacrifice data privacy. In this article, we propose a framework named Industrial Federated Topic Modeling (iFTM), in which multiple parties collaboratively train a high-quality topic model by simultaneously alleviating data scarcity and maintaining immunity to privacy adversaries.
Constraint-based Scheduling for Paint Shops in the Automotive Supply Industry
Felix Winter, Nysret Musliu
Factories in the automotive supply industry paint a large number of items requested by car manufacturing companies on a daily basis. As these factories face numerous constraints and optimization objectives, finding a good schedule becomes a challenging task in practice, and full-time employees are expected to manually create feasible production plans. In this study, we propose novel constraint programming models for a real-life paint shop scheduling problem. We evaluate and compare our models experimentally by performing a series of benchmark experiments using real-life instances in the industry.
Factories in the automotive supply industry paint a large number of items requested by car manufacturing companies on a daily basis. As these factories face numerous constraints and optimization objectives, finding a good schedule becomes a challenging task in practice, and full-time employees are expected to manually create feasible production plans. In this study, we propose novel constraint programming models for a real-life paint shop scheduling problem. We evaluate and compare our models experimentally by performing a series of benchmark experiments using real-life instances in the industry.
RHUPS: Mining Recent High Utility Patterns with Sliding Window–based Arrival Time Control over Data Streams
Yoonji Baek, Unil Yun, Heonho Kim, Hyoju Nam, Hyunsoo Kim, Jerry Chun-Wei Lin, Bay Vo, Witold Pedrycz
Databases that deal with the real world have various characteristics. New data is continuously inserted over time without limiting the length of the database, and a variety of information about the items constituting the database is contained. Recently generated data has a greater influence than the previously generated data. These are called the time-sensitive non-binary stream databases, and they include databases such as web-server click data, market sales data, data from sensor networks, and network traffic measurement. Many high utility pattern mining and stream pattern mining methods have been proposed so far. However, they have a limitation that they are not suitable to analyze these databases, because they find valid patterns by analyzing a database with only some of the features described above.
Databases that deal with the real world have various characteristics. New data is continuously inserted over time without limiting the length of the database, and a variety of information about the items constituting the database is contained. Recently generated data has a greater influence than the previously generated data. These are called the time-sensitive non-binary stream databases, and they include databases such as web-server click data, market sales data, data from sensor networks, and network traffic measurement. Many high utility pattern mining and stream pattern mining methods have been proposed so far. However, they have a limitation that they are not suitable to analyze these databases, because they find valid patterns by analyzing a database with only some of the features described above.
Deep Learning Thermal Image Translation for Night Vision Perception
Shuo Liu, Mingliang Gao, Vijay John, Zheng Liu, Erik Blasch
Context enhancement is critical for the environmental perception in night vision applications, especially for the dark night situation without sufficient illumination. In this article, we propose a thermal image translation method, which can translate thermal/infrared (IR) images into color visible (VI) images, called IR2VI. The IR2VI consists of two cascaded steps: translation from nighttime thermal IR images to gray-scale visible images (GVI), which is called IR-GVI; and the translation from GVI to color visible images (CVI), which is known as GVI-CVI in this article. For the first step, we develop the Texture-Net, a novel unsupervised image translation neural network based on generative adversarial networks.
Context enhancement is critical for the environmental perception in night vision applications, especially for the dark night situation without sufficient illumination. In this article, we propose a thermal image translation method, which can translate thermal/infrared (IR) images into color visible (VI) images, called IR2VI. The IR2VI consists of two cascaded steps: translation from nighttime thermal IR images to gray-scale visible images (GVI), which is called IR-GVI; and the translation from GVI to color visible images (CVI), which is known as GVI-CVI in this article. For the first step, we develop the Texture-Net, a novel unsupervised image translation neural network based on generative adversarial networks.
Uncovering Media Bias via Social Network Learning
Yiyi Zhou, Rongrong Ji, Jinsong Su, Jiaquan Yao
It is known that media outlets, such as CNN and FOX, have intrinsic political bias that is reflected in their news reports. The computational prediction of such bias has broad application prospects. However, the prediction is difficult via directly analyzing the news content without high-level context. In contrast, social signals (e.g., the network structure of media followers) provide inspiring cues to uncover such bias. In this article, we realize the first attempt of predicting the latent bias of media outlets by analyzing their social network structures. In particular, we address two key challenges: network sparsity and label sparsity. The network sparsity refers to the partial sampling of the entire follower network in practical analysis and computing, whereas the label sparsity refers to the difficulty of annotating sufficient labels to train the prediction model.
It is known that media outlets, such as CNN and FOX, have intrinsic political bias that is reflected in their news reports. The computational prediction of such bias has broad application prospects. However, the prediction is difficult via directly analyzing the news content without high-level context. In contrast, social signals (e.g., the network structure of media followers) provide inspiring cues to uncover such bias. In this article, we realize the first attempt of predicting the latent bias of media outlets by analyzing their social network structures. In particular, we address two key challenges: network sparsity and label sparsity. The network sparsity refers to the partial sampling of the entire follower network in practical analysis and computing, whereas the label sparsity refers to the difficulty of annotating sufficient labels to train the prediction model.
Self-weighted Robust LDA for Multiclass Classification with Edge Classes
Caixia Yan, Xiaojun Chang, Minnan Luo, Qinghua Zheng, Xiaoqin Zhang, Zhihui Li, Feiping Nie
Linear discriminant analysis (LDA) is a popular technique to learn the most discriminative features for multi-class classification. A vast majority of existing LDA algorithms are prone to be dominated by the class with very large deviation from the others, i.e., edge class, which occurs frequently in multi-class classification. First, the existence of edge classes often makes the total mean biased in the calculation of between-class scatter matrix. Second, the exploitation of ℓ2-norm based between-class distance criterion magnifies the extremely large distance corresponding to edge class. In this regard, a novel self-weighted robust LDA with ℓ2,1-norm based pairwise between-class distance criterion, called SWRLDA, is proposed for multi-class classification especially with edge classes.
Linear discriminant analysis (LDA) is a popular technique to learn the most discriminative features for multi-class classification. A vast majority of existing LDA algorithms are prone to be dominated by the class with very large deviation from the others, i.e., edge class, which occurs frequently in multi-class classification. First, the existence of edge classes often makes the total mean biased in the calculation of between-class scatter matrix. Second, the exploitation of ℓ2-norm based between-class distance criterion magnifies the extremely large distance corresponding to edge class. In this regard, a novel self-weighted robust LDA with ℓ2,1-norm based pairwise between-class distance criterion, called SWRLDA, is proposed for multi-class classification especially with edge classes.
On Representation Learning for Road Networks
Meng-Xiang Wang, Wang-Chien Lee, Tao-Yang Fu, Ge Yu
Informative representation of road networks is essential to a wide variety of applications on intelligent transportation systems. In this article, we design a new learning framework, called Representation Learning for Road Networks (RLRN), which explores various intrinsic properties of road networks to learn embeddings of intersections and road segments in road networks. To implement the RLRN framework, we propose a new neural network model, namely Road Network to Vector (RN2Vec), to learn embeddings of intersections and road segments jointly by exploring geo-locality and homogeneity of them, topological structure of the road networks, and moving behaviors of road users. In addition to model design, issues involving data preparation for model training are examined.
Informative representation of road networks is essential to a wide variety of applications on intelligent transportation systems. In this article, we design a new learning framework, called Representation Learning for Road Networks (RLRN), which explores various intrinsic properties of road networks to learn embeddings of intersections and road segments in road networks. To implement the RLRN framework, we propose a new neural network model, namely Road Network to Vector (RN2Vec), to learn embeddings of intersections and road segments jointly by exploring geo-locality and homogeneity of them, topological structure of the road networks, and moving behaviors of road users. In addition to model design, issues involving data preparation for model training are examined.
A Theoretical Revisit to Linear Convergence for Saddle Point Problems
Wendi Wu, Yawei Zhao, En Zhu, Xinwang Liu, Xingxing Zhang, Lailong Luo, Shixiong Wang, Jianping Yin
Recently, convex-concave bilinear Saddle Point Problems (SPP) is widely used in lasso problems, Support Vector Machines, game theory, and so on. Previous researches have proposed many methods to solve SPP, and present their convergence rate theoretically. To achieve linear convergence, analysis in those previouse studies requires strong convexity of &phis;(z). But, we find the linear convergence can also be achieved even for a general convex but not strongly convex &phis;(z). In the article, by exploiting the strong duality of SPP, we propose a new method to solve SPP, and achieve the linear convergence. We present a new general sufficient condition to achieve linear convergence, but do not require the strong convexity of &phis;(z).
Recently, convex-concave bilinear Saddle Point Problems (SPP) is widely used in lasso problems, Support Vector Machines, game theory, and so on. Previous researches have proposed many methods to solve SPP, and present their convergence rate theoretically. To achieve linear convergence, analysis in those previouse studies requires strong convexity of &phis;(z). But, we find the linear convergence can also be achieved even for a general convex but not strongly convex &phis;(z). In the article, by exploiting the strong duality of SPP, we propose a new method to solve SPP, and achieve the linear convergence. We present a new general sufficient condition to achieve linear convergence, but do not require the strong convexity of &phis;(z).