2021 IEEE International Conference on Data Mining (ICDM)最新文献_第2页

MetaEDL: Meta Evidential Learning For Uncertainty-Aware Cold-Start Recommendations MetaEDL:不确定性感知冷启动推荐的Meta证据学习

2021 IEEE International Conference on Data Mining (ICDM) Pub Date : 2021-12-01 DOI: 10.1109/ICDM51629.2021.00154

K. Neupane, Ervine Zheng, Qi Yu

{"title":"MetaEDL: Meta Evidential Learning For Uncertainty-Aware Cold-Start Recommendations","authors":"K. Neupane, Ervine Zheng, Qi Yu","doi":"10.1109/ICDM51629.2021.00154","DOIUrl":"https://doi.org/10.1109/ICDM51629.2021.00154","url":null,"abstract":"Recommender systems have been widely used to predict users’ interests and filter information from a large number of candidate items. However, accurately capturing the interests of users having limited interactions with a system remains a long-lasting challenge. Furthermore, existing recommender systems primarily focus on predicting user preferences without quantifying the prediction uncertainty. Uncertainty can help to quantify the model confidence when making a recommendation where low model confidence could serve as a more accurate indicator of a user’s cold-start level than simply using the number of interactions. We present a novel recommendation model that seamlessly integrates a meta-learning module with an evidential learning approach. The former module generalizes meta knowledge to tackle cold-start recommendations by exploiting fast adaptation. The latter quantifies both aleatoric and epistemic uncertainty without performing expensive posterior inference. Evidential learning achieves this by placing evidential priors and treating the output of the meta-learning module as evidence-based pseudo counts and learns a function to directly predict the evidence of a target interaction. Experiments on four benchmark datasets justify that our proposed model captures the uncertainty of users and demonstrates its superior performance over the state-of-the-art recommendation models.","PeriodicalId":320970,"journal":{"name":"2021 IEEE International Conference on Data Mining (ICDM)","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128072716","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}

引用次数: 5

Learning to Reweight Samples with Offline Loss Sequence 学习用离线损失序列重加权样本

2021 IEEE International Conference on Data Mining (ICDM) Pub Date : 2021-12-01 DOI: 10.1109/ICDM51629.2021.00083

Yuhua Wei, Xiaoyu Li, Jishang Wei, B. Qian, Chen Li

{"title":"Learning to Reweight Samples with Offline Loss Sequence","authors":"Yuhua Wei, Xiaoyu Li, Jishang Wei, B. Qian, Chen Li","doi":"10.1109/ICDM51629.2021.00083","DOIUrl":"https://doi.org/10.1109/ICDM51629.2021.00083","url":null,"abstract":"Deep neural networks (DNNs) provide the best of class solutions to many supervised tasks due to their powerful function fitting capabilities. However, it is challenging to handle data bias, such as label noise and class imbalance, when applying DNNs to solve real-world problems. Sample reweighting is a popular strategy to tackle data bias, which assigns higher weights to informative samples or samples with clean labels. However, conventional reweighting methods require prior knowledge of the distribution information of data bias, which is intractable in practice. In recent years, meta-learning-based methods have been proposed to learn to assign weights to training samples adaptively by using their online training loss or gradient directions. However, the latent bias distribution cannot be adequately characterized in an online fashion. The online loss distribution changes over the training procedure, making it even harder to perform the sample weight learning. In contrast to past methods, we propose a two-stage training strategy to tackle the above problems. In the first stage, the loss sequences of samples are collected. In the second stage, a subnet with convolutional layers is utilized to learn the mapping from offline sample loss sequence to sample weight adaptively. Guided by a small unbiased meta dataset, this subnet is optimized iteratively with the main classifier network in a meta-learning manner. Empirical results show that our method, called Meta Reweighting with Offline Loss Sequence (MROLS), outperforms state-of-the-art reweighting techniques on most benchmarks. Moreover, the weights of training samples learned via MROLS can be well utilized by other classifiers, which can directly enhance the standard training schema. Our source code is available at https://github.com/Neronjust2017/MROLS.","PeriodicalId":320970,"journal":{"name":"2021 IEEE International Conference on Data Mining (ICDM)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130936750","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}

引用次数: 0

GQNAS: Graph Q Network for Neural Architecture Search GQNAS:神经结构搜索的图Q网络

2021 IEEE International Conference on Data Mining (ICDM) Pub Date : 2021-12-01 DOI: 10.1109/ICDM51629.2021.00159

Yi Qin, Xin Wang, Peng Cui, Wenwu Zhu

{"title":"GQNAS: Graph Q Network for Neural Architecture Search","authors":"Yi Qin, Xin Wang, Peng Cui, Wenwu Zhu","doi":"10.1109/ICDM51629.2021.00159","DOIUrl":"https://doi.org/10.1109/ICDM51629.2021.00159","url":null,"abstract":"Neural Architecture Search (NAS), aiming to automatically search for neural structure that performs the best, has attracted lots of attentions from both the academy and industry. However, most existing works assume each layer accepts a fixed number of inputs from previous layers, ignoring the flexibility of receiving inputs from an arbitrary number of previous layers. Allowing to receive inputs from an arbitrary number of layers benefits in introducing far more possible combinations of connections among layers, which may also result in much more complex structural relations in architectures. Existing works fail to capture structural correlations among different layers, thus limiting the ability to discover the optimal architecture. To overcome the weakness of existing methods, we study the NAS problem by assuming an arbitrary number of inputs for each layer and capturing the structural correlations among different layers in this paper. Nevertheless, besides the complex structural correlations, considering an arbitrary number of inputs for each layer may also lead to a fully connected structure with up to O(n2) connections for n layers, posing great challenges to efficiently handle polynomial numbers of connections among different layers. To tackle this challenge, we propose a Graph Q Network for NAS (GQNAS), where the states and actions are redefined for searching architectures with input from an arbitrary number of layers. Concretely, we regard a neural architecture as a directed acyclic graph and use graph neural network (GNN) as the Q-function approximation in deep Q network (DQN) to capture the complex structural relations between different layers for obtaining accurate Q-values. Our extensive experiments show that the proposed GQNAS model is able to achieve better performances than several state-of-the-art approaches.","PeriodicalId":320970,"journal":{"name":"2021 IEEE International Conference on Data Mining (ICDM)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124178361","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}

引用次数: 11

Spikelet: An Adaptive Symbolic Approximation for Finding Higher-Level Structure in Time Series 小穗:在时间序列中寻找高级结构的自适应符号逼近

2021 IEEE International Conference on Data Mining (ICDM) Pub Date : 2021-12-01 DOI: 10.1109/ICDM51629.2021.00132

Makoto Imamura, Takaaki Nakamura

{"title":"Spikelet: An Adaptive Symbolic Approximation for Finding Higher-Level Structure in Time Series","authors":"Makoto Imamura, Takaaki Nakamura","doi":"10.1109/ICDM51629.2021.00132","DOIUrl":"https://doi.org/10.1109/ICDM51629.2021.00132","url":null,"abstract":"Time series motifs have become a fundamental tool to characterize repeated and conserved structures in systems, such as manufacturing, human behavior and economic activities. Recently the notion of semantic motif was introduced as a generalization of motifs that allows the capture of higher-level semantic structure. Sematic motifs are a very promising primitive; however, the original work characterizes a semantic motif with only two sub-patterns separated by a variable length don’t-care region, so it may fail to capture certain types of regularities embedded in a time series. To mitigate this weakness, we propose an adaptive, symbolic and spike-based approximation that allows overlapping segmentation, which we call spikelet. The adaptive and overlapping nature of our representation is more expressive, enabling it to capture both global and local characteristics of a conserved structure. Furthermore, the symbolic nature of our proposed representation enables us to reason about the “grammatical” structure of the data. With extensive empirical work, we show that spikelet-based algorithms are scalable enough for real-world datasets and enables us to find the higher-level structure that would otherwise escape our attention.","PeriodicalId":320970,"journal":{"name":"2021 IEEE International Conference on Data Mining (ICDM)","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114473879","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}

引用次数: 1

A Multi-view Confidence-calibrated Framework for Fair and Stable Graph Representation Learning 公平稳定图表示学习的多视图置信度校准框架

2021 IEEE International Conference on Data Mining (ICDM) Pub Date : 2021-12-01 DOI: 10.1109/ICDM51629.2021.00194

Xu Zhang, Liang Zhang, Bo Jin, Xinjiang Lu

{"title":"A Multi-view Confidence-calibrated Framework for Fair and Stable Graph Representation Learning","authors":"Xu Zhang, Liang Zhang, Bo Jin, Xinjiang Lu","doi":"10.1109/ICDM51629.2021.00194","DOIUrl":"https://doi.org/10.1109/ICDM51629.2021.00194","url":null,"abstract":"Graph Neural Networks (GNNs) are prone to adversarial attacks and discriminatory biases. The cutting-edge studies usually adopt a perturbation-invariant consistency regularization strategy without considering the inherent prediction uncertainties, which can lead to unsatisfactory overconfidence for incorrect prediction under intent graph topology or node features attacks. Besides, operating on the complete graph structure is biased towards global level graph noise and brings severe computational issues. In this work, we develop a multi-view confidence-calibrated framework, called MCCNIFTY, for unified fair and stable graph representation learning. At its core is a multi-view uncertainty-aware node embedding learning module derived from evidential theory, including an intra-view evidence calibration, an inter-view evidence fusion, and an uncertainty-aware message passing process in a GNN architecture, which simultaneously optimizes for counterfactual fairness and stability at the sub-graph level. Experimental results on three real-world datasets demonstrate that our method is capable of adequately capturing inherent uncertainties while improving the fairness and stability via subgraph-induced multiview confidence calibration.","PeriodicalId":320970,"journal":{"name":"2021 IEEE International Conference on Data Mining (ICDM)","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114601516","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}

引用次数: 3

Overfitting Avoidance in Tensor Train Factorization and Completion: Prior Analysis and Inference 张量训练分解与补全中的过拟合避免:先验分析与推理

2021 IEEE International Conference on Data Mining (ICDM) Pub Date : 2021-12-01 DOI: 10.1109/ICDM51629.2021.00185

Le Xu, Lei Cheng, Ngai Wong, Yik-Chung Wu

引用次数: 7

TEST-GCN: Topologically Enhanced Spatial-Temporal Graph Convolutional Networks for Traffic Forecasting 基于拓扑增强时空图卷积网络的交通预测

2021 IEEE International Conference on Data Mining (ICDM) Pub Date : 2021-12-01 DOI: 10.1109/ICDM51629.2021.00110

Muhammad Afif Ali, Suriya Venkatesan, Victor Liang, H. Kruppa

{"title":"TEST-GCN: Topologically Enhanced Spatial-Temporal Graph Convolutional Networks for Traffic Forecasting","authors":"Muhammad Afif Ali, Suriya Venkatesan, Victor Liang, H. Kruppa","doi":"10.1109/ICDM51629.2021.00110","DOIUrl":"https://doi.org/10.1109/ICDM51629.2021.00110","url":null,"abstract":"Accurate traffic forecasting is a fundamental challenge of location-based systems. Recent works were able to achieve state-of-the-art results by incorporating Graph Convolutional Networks (GCN) to capture spatial dependencies in the data. However, these works rely on a fixed latent feature representation of the underlying graph structure, failing to exploit the rich spatial information offered by the road network. In this paper, we propose the Topologically Enhanced Spatial-Temporal Graph Convolutional Network (TEST-GCN), a novel graph convolution model for road traffic speed forecasting based on floating car data, aiming to better capture the spatial dependencies in the data by fully exploiting the characteristics of the road network. We introduce the node and edge embedding layers, using topological attributes to iteratively improve the latent feature representation of the road network. We show that our model effectively captures both spatial and temporal dependencies in the data, consistently outperforming state-of-the-art methods in road traffic speed prediction, achieving approximately 50 % reduction in model size and 33% improvement in empirical computational times.","PeriodicalId":320970,"journal":{"name":"2021 IEEE International Conference on Data Mining (ICDM)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123580361","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}

引用次数: 5

Graph Neighborhood Routing and Random Walk for Session-based Recommendation 基于会话推荐的图邻域路由和随机行走

2021 IEEE International Conference on Data Mining (ICDM) Pub Date : 2021-12-01 DOI: 10.1109/ICDM51629.2021.00198

Zizhuo Zhang, Bang Wang

{"title":"Graph Neighborhood Routing and Random Walk for Session-based Recommendation","authors":"Zizhuo Zhang, Bang Wang","doi":"10.1109/ICDM51629.2021.00198","DOIUrl":"https://doi.org/10.1109/ICDM51629.2021.00198","url":null,"abstract":"Session-based recommendation (SBR) is to predict the next item for an anonymous item sequence. Although many neural models have proven effectiveness in the SBR task, how to learn better items’ embeddings for neural models still remains a key challenge due to the anonymity of sessions and sparsity of users’ behaviors. This paper proposes a graph-based neural model, called Graph N eighborhood Routing and Random Walk (GNRRW), which learns two kinds of item embeddings for the SBR task. We first construct an item graph based on items’ co-occurrences in all sessions, on which we learn a local embedding and a global embedding for each item. For local embedding learning, we propose a novel neighborhood routing (NR) algorithm to exploit the compositive relations between an item and its neighbors. The NR algorithm has an excellent feature in that no additional parameters are needed in the training process. For global embedding learning, we propose a random walk-based approach to explore a kind of global relations between an item and representative items. Furthermore, we propose a switch-based shared gated recurrent unit (GRU) network to alternatively learn session local representation to make a local prediction, and learn session global representation to make a global prediction. Finally, we design a decision fusion mechanism to adaptively fuse both local and global predictions to output final items’ preference scores. Experiments on the public Yoochoose and Diginetica dataset validate the superiority of our GNRRW model over the state-of-the-art neural models.","PeriodicalId":320970,"journal":{"name":"2021 IEEE International Conference on Data Mining (ICDM)","volume":"142 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122129034","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}

引用次数: 4

Deep Incremental RNN for Learning Sequential Data: A Lyapunov Stable Dynamical System 用于序列数据学习的深度增量RNN:一个Lyapunov稳定动力系统

2021 IEEE International Conference on Data Mining (ICDM) Pub Date : 2021-12-01 DOI: 10.1109/ICDM51629.2021.00108

Ziming Zhang, Guojun Wu, Yanhua Li, Yun Yue, Xun Zhou

{"title":"Deep Incremental RNN for Learning Sequential Data: A Lyapunov Stable Dynamical System","authors":"Ziming Zhang, Guojun Wu, Yanhua Li, Yun Yue, Xun Zhou","doi":"10.1109/ICDM51629.2021.00108","DOIUrl":"https://doi.org/10.1109/ICDM51629.2021.00108","url":null,"abstract":"With the recent advances in mobile sensing technologies, large amounts of sequential data are collected, such as vehicle GPS records, stock prices, sensor data from air quality detectors. Recurrent neural networks (RNNs) have been studied extensively to learn complex patterns for sequential data, with applicatons in natural language processing for sentence prediction/completion, human activity recognition for predicting or classifying human activities. However, there are many practical issues when training RNNs, e.g., vanishing and exploding gradients often occur due to the repeatability of network weights, etc. In this paper, we study the training stability in deep recurrent neural networks (RNNs), and propose a novel network, namely, deep incremental RNN (DIRNN). In contrast to the literature, we prove that DIRNN is essentially a Lyapunov stable dynamical system where there is no vanishing or exploding gradient in training. To demonstrate the applicability in practice, we also propose a novel implementation, namely TinyRNN, that sparsifies the transition matrices in DIRNN using weighted random permutations to reduce the model sizes. We evaluate our approach on seven benchmark datasets, and achieve state-of-the-art results. Demo code is provided in the supplementary file.","PeriodicalId":320970,"journal":{"name":"2021 IEEE International Conference on Data Mining (ICDM)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126111921","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}

引用次数: 4

Physics-Guided Machine Learning from Simulation Data: An Application in Modeling Lake and River Systems 基于模拟数据的物理引导机器学习:在湖泊和河流系统建模中的应用

2021 IEEE International Conference on Data Mining (ICDM) Pub Date : 2021-12-01 DOI: 10.1109/ICDM51629.2021.00037

X. Jia, Yiqun Xie, Sheng Li, Shengyu Chen, J. Zwart, J. Sadler, A. Appling, S. Oliver, J. Read

{"title":"Physics-Guided Machine Learning from Simulation Data: An Application in Modeling Lake and River Systems","authors":"X. Jia, Yiqun Xie, Sheng Li, Shengyu Chen, J. Zwart, J. Sadler, A. Appling, S. Oliver, J. Read","doi":"10.1109/ICDM51629.2021.00037","DOIUrl":"https://doi.org/10.1109/ICDM51629.2021.00037","url":null,"abstract":"This paper proposes a new physics-guided machine learning approach that incorporates the scientific knowledge in physics-based models into machine learning models. Physics-based models are widely used to study dynamical systems in a variety of scientific and engineering problems. Although they are built based on general physical laws that govern the relations from input to output variables, these models often produce biased simulations due to inaccurate parameterizations or approximations used to represent the true physics. In this paper, we aim to build a new data-driven framework to monitor dynamical systems by extracting general scientific knowledge embodied in simulation data generated by the physics-based model. To handle the bias in simulation data caused by imperfect parameterization, we propose to extract general physical relations jointly from multiple sets of simulations generated by a physics-based model under different physical parameters. In particular, we develop a spatio-temporal network architecture that uses its gating variables to capture the variation of physical parameters. We initialize this model using a pre-training strategy that helps discover common physical patterns shared by different sets of simulation data. Then we fine-tune it using limited observation data via a contrastive learning process. By leveraging the complementary strength of machine learning and domain knowledge, our method has been shown to produce accurate predictions, use less training samples and generalize to out-of-sample scenarios. We further show that the method can provide insights about the variation of physical parameters over space and time in two domain applications: predicting temperature in streams and predicting temperature in lakes.","PeriodicalId":320970,"journal":{"name":"2021 IEEE International Conference on Data Mining (ICDM)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127201916","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}

引用次数: 5