Efficient Heterogeneous Collaborative Filtering without Negative Sampling for Recommendation

Recent studies on recommendation have largely focused on exploring state-of-the-art neural networks to improve the expressiveness of models, while typically apply the Negative Sampling (NS) strategy for efficient learning. Despite effectiveness, two important issues have not been well-considered in existing methods: 1) NS suffers from dramatic fluctuation, making sampling-based methods difficult to achieve the optimal ranking performance in practical applications; 2) although heterogeneous feedback (e.g., view, click, and purchase) is widespread in many online systems, most existing methods leverage only one primary type of user feedback such as purchase. In this work, we propose a novel non-sampling transfer learning solution, named Efficient Heterogeneous Collaborative Filtering (EHCF) for Top-N recommendation. It can not only model fine-grained user-item relations, but also efficiently learn model parameters from the whole heterogeneous data (including all unlabeled data) with a rather low time complexity. Extensive experiments on three real-world datasets show that EHCF significantly outperforms state-of-the-art recommendation methods in both traditional (single-behavior) and heterogeneous scenarios. Moreover, EHCF shows significant improvements in training efficiency, making it more applicable to real-world large-scale systems. Our implementation has been released 1 to facilitate further developments on efficient whole-data based neural methods.

Download Full-text

Discrete Trust-aware Matrix Factorization for Fast Recommendation

Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence ◽

10.24963/ijcai.2019/191 ◽

2019 ◽

Author(s):

Guibing Guo ◽

Enneng Yang ◽

Li Shen ◽

Xiaochun Yang ◽

Xiaodong He

Keyword(s):

Social Influence ◽

Collaborative Filtering ◽

Recommender Systems ◽

Social Relations ◽

Real World ◽

Matrix Factorization ◽

State Of The Art ◽

Proposed Model ◽

Hamming Space ◽

Real World Datasets

Trust-aware recommender systems have received much attention recently for their abilities to capture the influence among connected users. However, they suffer from the efficiency issue due to large amount of data and time-consuming real-valued operations. Although existing discrete collaborative filtering may alleviate this issue to some extent, it is unable to accommodate social influence. In this paper we propose a discrete trust-aware matrix factorization (DTMF) model to take dual advantages of both social relations and discrete technique for fast recommendation. Specifically, we map the latent representation of users and items into a joint hamming space by recovering the rating and trust interactions between users and items. We adopt a sophisticated discrete coordinate descent (DCD) approach to optimize our proposed model. In addition, experiments on two real-world datasets demonstrate the superiority of our approach against other state-of-the-art approaches in terms of ranking accuracy and efficiency.

Download Full-text

Multi-Scale Shape Adaptive Network for Raindrop Detection and Removal from a Single Image

Sensors ◽

10.3390/s20236733 ◽

2020 ◽

Vol 20 (23) ◽

pp. 6733

Author(s):

Hao Luo ◽

Qingbo Wu ◽

King Ngi Ngan ◽

Hanxiao Luo ◽

Haoran Wei ◽

...

Keyword(s):

Real World ◽

Large Scale ◽

State Of The Art ◽

Limited Capacity ◽

Single Image ◽

Adaptive Network ◽

Multi Scale ◽

Shape Invariant ◽

Large Scale Dataset ◽

Real World Datasets

Removing raindrops from a single image is a challenging problem due to the complex changes in shape, scale, and transparency among raindrops. Previous explorations have mainly been limited in two ways. First, publicly available raindrop image datasets have limited capacity in terms of modeling raindrop characteristics (e.g., raindrop collision and fusion) in real-world scenes. Second, recent deraining methods tend to apply shape-invariant filters to cope with diverse rainy images and fail to remove raindrops that are especially varied in shape and scale. In this paper, we address these raindrop removal problems from two perspectives. First, we establish a large-scale dataset named RaindropCityscapes, which includes 11,583 pairs of raindrop and raindrop-free images, covering a wide variety of raindrops and background scenarios. Second, a two-branch Multi-scale Shape Adaptive Network (MSANet) is proposed to detect and remove diverse raindrops, effectively filtering the occluded raindrop regions and keeping the clean background well-preserved. Extensive experiments on synthetic and real-world datasets demonstrate that the proposed method achieves significant improvements over the recent state-of-the-art raindrop removal methods. Moreover, the extension of our method towards the rainy image segmentation and detection tasks validates the practicality of the proposed method in outdoor applications.

Download Full-text

Review Summary Generation in Online Systems: Frameworks for Supervised and Unsupervised Scenarios

ACM Transactions on the Web ◽

10.1145/3448015 ◽

2021 ◽

Vol 15 (3) ◽

pp. 1-33

Author(s):

Wenjun Jiang ◽

Jing Chen ◽

Xiaofei Ding ◽

Jie Wu ◽

Jiawei He ◽

...

Keyword(s):

Decision Making ◽

Real World ◽

Text Summarization ◽

Experimental Results ◽

Product Review ◽

Comprehensive Review ◽

Online Systems ◽

Real World Datasets ◽

Different Characteristics

In online systems, including e-commerce platforms, many users resort to the reviews or comments generated by previous consumers for decision making, while their time is limited to deal with many reviews. Therefore, a review summary, which contains all important features in user-generated reviews, is expected. In this article, we study “how to generate a comprehensive review summary from a large number of user-generated reviews.” This can be implemented by text summarization, which mainly has two types of extractive and abstractive approaches. Both of these approaches can deal with both supervised and unsupervised scenarios, but the former may generate redundant and incoherent summaries, while the latter can avoid redundancy but usually can only deal with short sequences. Moreover, both approaches may neglect the sentiment information. To address the above issues, we propose comprehensive Review Summary Generation frameworks to deal with the supervised and unsupervised scenarios. We design two different preprocess models of re-ranking and selecting to identify the important sentences while keeping users’ sentiment in the original reviews. These sentences can be further used to generate review summaries with text summarization methods. Experimental results in seven real-world datasets (Idebate, Rotten Tomatoes Amazon, Yelp, and three unlabelled product review datasets in Amazon) demonstrate that our work performs well in review summary generation. Moreover, the re-ranking and selecting models show different characteristics.

Download Full-text

Extrinsic Camera Calibration with Line-Laser Projection

Sensors ◽

10.3390/s21041091 ◽

2021 ◽

Vol 21 (4) ◽

pp. 1091

Author(s):

Izaak Van Crombrugge ◽

Rudi Penne ◽

Steve Vanlanduit

Keyword(s):

Camera Calibration ◽

Real World ◽

Large Scale ◽

State Of The Art ◽

Bundle Adjustment ◽

Field Of View ◽

Extrinsic Calibration ◽

Practical Procedure ◽

Partial Overlap

Knowledge of precise camera poses is vital for multi-camera setups. Camera intrinsics can be obtained for each camera separately in lab conditions. For fixed multi-camera setups, the extrinsic calibration can only be done in situ. Usually, some markers are used, like checkerboards, requiring some level of overlap between cameras. In this work, we propose a method for cases with little or no overlap. Laser lines are projected on a plane (e.g., floor or wall) using a laser line projector. The pose of the plane and cameras is then optimized using bundle adjustment to match the lines seen by the cameras. To find the extrinsic calibration, only a partial overlap between the laser lines and the field of view of the cameras is needed. Real-world experiments were conducted both with and without overlapping fields of view, resulting in rotation errors below 0.5°. We show that the accuracy is comparable to other state-of-the-art methods while offering a more practical procedure. The method can also be used in large-scale applications and can be fully automated.

Download Full-text

Attention Enhanced Serial Unet++ Network for Removing Unevenly Distributed Haze

Electronics ◽

10.3390/electronics10222868 ◽

2021 ◽

Vol 10 (22) ◽

pp. 2868

Author(s):

Wenxuan Zhao ◽

Yaqin Zhao ◽

Liqi Feng ◽

Jiaxi Tang

Keyword(s):

Neural Network ◽

Convolutional Neural Network ◽

Real World ◽

Large Scale ◽

Learning Strategy ◽

Contextual Information ◽

Small Scale ◽

Image Dehazing ◽

Atmospheric Scattering ◽

Real World Datasets

The purpose of image dehazing is the reduction of the image degradation caused by suspended particles for supporting high-level visual tasks. Besides the atmospheric scattering model, convolutional neural network (CNN) has been used for image dehazing. However, the existing image dehazing algorithms are limited in face of unevenly distributed haze and dense haze in real-world scenes. In this paper, we propose a novel end-to-end convolutional neural network called attention enhanced serial Unet++ dehazing network (AESUnet) for single image dehazing. We attempt to build a serial Unet++ structure that adopts a serial strategy of two pruned Unet++ blocks based on residual connection. Compared with the simple Encoder–Decoder structure, the serial Unet++ module can better use the features extracted by encoders and promote contextual information fusion in different resolutions. In addition, we take some improvement measures to the Unet++ module, such as pruning, introducing the convolutional module with ResNet structure, and a residual learning strategy. Thus, the serial Unet++ module can generate more realistic images with less color distortion. Furthermore, following the serial Unet++ blocks, an attention mechanism is introduced to pay different attention to haze regions with different concentrations by learning weights in the spatial domain and channel domain. Experiments are conducted on two representative datasets: the large-scale synthetic dataset RESIDE and the small-scale real-world datasets I-HAZY and O-HAZY. The experimental results show that the proposed dehazing network is not only comparable to state-of-the-art methods for the RESIDE synthetic datasets, but also surpasses them by a very large margin for the I-HAZY and O-HAZY real-world dataset.

Download Full-text

Self-Paced Robust Learning for Leveraging Clean Labels in Noisy Data

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v34i04.6166 ◽

2020 ◽

Vol 34 (04) ◽

pp. 6853-6860

Author(s):

Xuchao Zhang ◽

Xian Wu ◽

Fanglan Chen ◽

Liang Zhao ◽

Chang-Tien Lu

Keyword(s):

Real World ◽

Large Scale ◽

Learning Algorithm ◽

Noisy Data ◽

Training Set ◽

Robust Learning ◽

Robust Model ◽

Small Set ◽

Real World Datasets ◽

Theoretical Analyses

The success of training accurate models strongly depends on the availability of a sufficient collection of precisely labeled data. However, real-world datasets contain erroneously labeled data samples that substantially hinder the performance of machine learning models. Meanwhile, well-labeled data is usually expensive to obtain and only a limited amount is available for training. In this paper, we consider the problem of training a robust model by using large-scale noisy data in conjunction with a small set of clean data. To leverage the information contained via the clean labels, we propose a novel self-paced robust learning algorithm (SPRL) that trains the model in a process from more reliable (clean) data instances to less reliable (noisy) ones under the supervision of well-labeled data. The self-paced learning process hedges the risk of selecting corrupted data into the training set. Moreover, theoretical analyses on the convergence of the proposed algorithm are provided under mild assumptions. Extensive experiments on synthetic and real-world datasets demonstrate that our proposed approach can achieve a considerable improvement in effectiveness and robustness to existing methods.

Download Full-text

Legal Judgment Prediction Based on Multiclass Information Fusion

Complexity ◽

10.1155/2020/3089189 ◽

2020 ◽

Vol 2020 ◽

pp. 1-12

Author(s):

Kongfan Zhu ◽

Rundong Guo ◽

Weifeng Hu ◽

Zeqiang Li ◽

Yujun Li

Keyword(s):

Information Fusion ◽

Real World ◽

Large Scale ◽

State Of The Art ◽

External Information ◽

Criminal Cases ◽

Law System ◽

Large Scale Dataset ◽

Assistant Systems ◽

Civil Law System

Legal judgment prediction (LJP), as an effective and critical application in legal assistant systems, aims to determine the judgment results according to the information based on the fact determination. In real-world scenarios, to deal with the criminal cases, judges not only take advantage of the fact description, but also consider the external information, such as the basic information of defendant and the court view. However, most existing works take the fact description as the sole input for LJP and ignore the external information. We propose a Transformer-Hierarchical-Attention-Multi-Extra (THME) Network to make full use of the information based on the fact determination. We conduct experiments on a real-world large-scale dataset of criminal cases in the civil law system. Experimental results show that our method outperforms state-of-the-art LJP methods on all judgment prediction tasks.

Download Full-text

Generalized velocity–density model based on microscopic traffic simulation

Transport ◽

10.3846/16484142.2017.1292950 ◽

2017 ◽

Vol 33 (2) ◽

pp. 489-501 ◽

Cited By ~ 1

Author(s):

Oussama Derbel ◽

Tamás Péter ◽

Benjamin Mourllion ◽

Michel Basset

Keyword(s):

Large Scale ◽

Interpolation Method ◽

Function Class ◽

Density Model ◽

Driver Model ◽

Practical Significance ◽

Model Parameters ◽

Practical Applications ◽

Velocity Models ◽

Traffic Characteristics

In case of the Intelligent Driver Model (IDM) the actual Velocity–Density law V(D) applied by this dynamic system is not defined, only the dynamic behaviour of the vehicles/drivers is determined. Therefore, the logical question is whether the related investigations enhance an existing and known law or reveal a new connection. Specifically, which function class/type is enhanced by the IDM? The publication presents a model analysis, the goal of which was the exploration of a feature of the IDM, which, as yet, ‘remained hidden’. The theoretical model results are useful, this analysis important in the practice in the field of hybrid control as well. The transfer of the IDM groups through large-scale networks has special practical significance. For example, in convoys, groups of special vehicle, safety measures with delegations. In this case, the large-scale network traffic characteristics and the IDM traffic characteristics should be taken into account simultaneously. Important characteristics are the speed–density laws. In case of effective modelling of large networks macroscopic models are used, however the IDMs are microscopic. With careful modelling, we cannot be in contradiction with the application of speed–density law, where there IDM convoy passes. Therefore, in terms of practical applications, it is important to recognize what kind of speed–density law is applied by the IDM convoys in traffic. Therefore, in our case the goal was not the validation of the model, but the exploration of a further feature of the validated model. The separate validation of the model was not necessary, since many validated applications for this model have been demonstrated in practice. In our calculations, also the applied model parameter values remained in the range of the model parameters used in the literature. This paper presents a new approach for Velocity–Density Model (VDM) synthesis. It consists in modelling separately each of the density and the velocity (macroscopic parameter). From this study, safety time headway (microscopic parameter) can be identified from macroscopic data by mean of interpolation method in the developed map of velocity–density. By combining the density and the velocity models, a generalized new VDM is developed. It is shown that from this one, some literature VDMs, as well as their properties, can be derived by fixing some of its parameters.

Download Full-text

Learning Compact Model for Large-Scale Multi-Label Data

Proceedings of the AAAI Conference on Artificial Intelligence ◽

10.1609/aaai.v33i01.33015385 ◽

2019 ◽

Vol 33 ◽

pp. 5385-5392 ◽

Cited By ~ 2

Author(s):

Tong Wei ◽

Yu-Feng Li

Keyword(s):

Large Scale ◽

Optimization Problem ◽

Performance Metrics ◽

State Of The Art ◽

Optimization Method ◽

Model Parameters ◽

Generalization Capability ◽

Constrained Optimization Problem ◽

Unseen Data ◽

Model Size

Large-scale multi-label learning (LMLL) aims to annotate relevant labels from a large number of candidates for unseen data. Due to the high dimensionality in both feature and label spaces in LMLL, the storage overheads of LMLL models are often costly. This paper proposes a POP (joint label and feature Parameter OPtimization) method. It tries to filter out redundant model parameters to facilitate compact models. Our key insights are as follows. First, we investigate labels that have little impact on the commonly used LMLL performance metrics and only preserve a small number of dominant parameters for these labels. Second, for the remaining influential labels, we reduce spurious feature parameters that have little contribution to the generalization capability of models, and preserve parameters for only discriminative features. The overall problem is formulated as a constrained optimization problem pursuing minimal model size. In order to solve the resultant difficult optimization, we show that a relaxation of the optimization can be efficiently solved using binary search and greedy strategies. Experiments verify that the proposed method clearly reduces the model size compared to state-of-the-art LMLL approaches, in addition, achieves highly competitive performance.

Download Full-text

Expert Detection and Recommendation Model With User-Generated Tags in Collaborative Tagging Systems

Journal of Database Management ◽

10.4018/jdm.2020100102 ◽

2020 ◽

Vol 31 (4) ◽

pp. 24-45

Author(s):

Mengmeng Shen ◽

Jun Wang ◽

Ou Liu ◽

Haiying Wang

Keyword(s):

Collaborative Filtering ◽

Community Detection ◽

Real World ◽

Agglomerative Hierarchical Clustering ◽

Collaborative Tagging ◽

Excellent Performance ◽

Recommendation Algorithm ◽

Proposed Model ◽

Target User ◽

Real World Datasets

Tags generated in collaborative tagging systems (CTSs) may help users describe, categorize, search, discover, and navigate content, whereas the difficulty is how to go beyond the information explosion and obtain experts and the required information quickly and accurately. This paper proposes an expert detection and recommendation (EDAR) model based on semantics of tags; the framework consists of community detection and EDAR. Specifically, this paper firstly mines communities based on an improved agglomerative hierarchical clustering (I-AHC) to cluster tags and then presents a community expert detection (CED) algorithm for identifying community experts, and finally, an expert recommendation algorithm is proposed based the improved collaborative filtering (CF) algorithm to recommend relevant experts for the target user. Experiments are carried out on real world datasets, and the results from data experiments and user evaluations have shown that the proposed model can provide excellent performance compared to the benchmark method.

Download Full-text