Tara Safavi, Adam Fourney, Robert B Sim, Marcin Juraszek, Shane Williams, Ned Friend, Danai Koutra, Paul N. Bennett
Individuals' personal information collections (their emails, files, appointments, web searches, contacts, etc) offer a wealth of insights into the organization and structure of their everyday lives. In this paper we address the task of learning representations of personal information items to capture individuals' ongoing activities, such as projects and tasks: Such representations can be used in activity-centric applications like personal assistants, email clients, and productivity tools to help people better manage their data and time. We propose a graph-based approach that leverages the inherent interconnected structure of personal information collections, and derive efficient, exact techniques to incrementally update representations as new data arrive. We demonstrate the strengths of our graph-based representations against competitive baselines in a novel intrinsic rating task and an extrinsic recommendation task.
{"title":"Toward Activity Discovery in the Personal Web","authors":"Tara Safavi, Adam Fourney, Robert B Sim, Marcin Juraszek, Shane Williams, Ned Friend, Danai Koutra, Paul N. Bennett","doi":"10.1145/3336191.3371828","DOIUrl":"https://doi.org/10.1145/3336191.3371828","url":null,"abstract":"Individuals' personal information collections (their emails, files, appointments, web searches, contacts, etc) offer a wealth of insights into the organization and structure of their everyday lives. In this paper we address the task of learning representations of personal information items to capture individuals' ongoing activities, such as projects and tasks: Such representations can be used in activity-centric applications like personal assistants, email clients, and productivity tools to help people better manage their data and time. We propose a graph-based approach that leverages the inherent interconnected structure of personal information collections, and derive efficient, exact techniques to incrementally update representations as new data arrive. We demonstrate the strengths of our graph-based representations against competitive baselines in a novel intrinsic rating task and an extrinsic recommendation task.","PeriodicalId":319008,"journal":{"name":"Proceedings of the 13th International Conference on Web Search and Data Mining","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123121542","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}
Expert finding is a task designed to enable recommendation of the right person who can provide high-quality answers to a requester's question. Most previous works try to involve a content-based recommendation, which only superficially comprehends the relevance between a requester's question and the expertise of candidate experts by exploring the content or topic similarity between the requester's question and the candidate experts' historical answers. However, if a candidate expert has never answered a question similar to the requester's question, then existing methods have difficulty making a correct recommendation. Therefore, exploring the implicit relevance between a requester's question and a candidate expert's historical records by perception and reasoning should be taken into consideration. In this study, we propose a novel textslrecurrent memory reasoning network (RMRN) to perform this task. This method focuses on different parts of a question, and accordingly retrieves information from the histories of the candidate expert.Since only a small percentage of historical records are relevant to any requester's question, we introduce a Gumbel-Softmax-based mechanism to select relevant historical records from candidate experts' answering histories. To evaluate the proposed method, we constructed two large-scale datasets drawn from Stack Overflow and Yahoo! Answer. Experimental results on the constructed datasets demonstrate that the proposed method could achieve better performance than existing state-of-the-art methods.
{"title":"Recurrent Memory Reasoning Network for Expert Finding in Community Question Answering","authors":"Jinlan Fu, Yi Li, Qi Zhang, Qinzhuo Wu, Renfeng Ma, Xuanjing Huang, Yu-Gang Jiang","doi":"10.1145/3336191.3371817","DOIUrl":"https://doi.org/10.1145/3336191.3371817","url":null,"abstract":"Expert finding is a task designed to enable recommendation of the right person who can provide high-quality answers to a requester's question. Most previous works try to involve a content-based recommendation, which only superficially comprehends the relevance between a requester's question and the expertise of candidate experts by exploring the content or topic similarity between the requester's question and the candidate experts' historical answers. However, if a candidate expert has never answered a question similar to the requester's question, then existing methods have difficulty making a correct recommendation. Therefore, exploring the implicit relevance between a requester's question and a candidate expert's historical records by perception and reasoning should be taken into consideration. In this study, we propose a novel textslrecurrent memory reasoning network (RMRN) to perform this task. This method focuses on different parts of a question, and accordingly retrieves information from the histories of the candidate expert.Since only a small percentage of historical records are relevant to any requester's question, we introduce a Gumbel-Softmax-based mechanism to select relevant historical records from candidate experts' answering histories. To evaluate the proposed method, we constructed two large-scale datasets drawn from Stack Overflow and Yahoo! Answer. Experimental results on the constructed datasets demonstrate that the proposed method could achieve better performance than existing state-of-the-art methods.","PeriodicalId":319008,"journal":{"name":"Proceedings of the 13th International Conference on Web Search and Data Mining","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114212491","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}
Mobility prediction, which is to predict where a user will arrive based on the user's historical mobility records, has attracted much attention. We argue that it is more useful to know not only where but also when a user will arrive next in many scenarios such as targeted advertising and taxi service. In this paper, we propose a novel context-aware deep model called DeepJMT for jointly performing mobility prediction (to know where) and time prediction (to know when). The DeepJMT model consists of (1) a hierarchical recurrent neural network (RNN) based sequential dependency encoder, which is more capable of capturing a user's mobility regularities and temporal patterns compared to vanilla RNN based models; (2) a spatial context extractor and a periodicity context extractor to extract location semantics and the user's periodicity, respectively; and (3) a co-attention based social & temporal context extractor which could extract the mobility and temporal evidence from social relationships. Experiments conducted on three real-world datasets show that DeepJMT outperforms the state-of-the-art mobility prediction and time prediction methods.
{"title":"Context-aware Deep Model for Joint Mobility and Time Prediction","authors":"Yile Chen, Cheng Long, G. Cong, Chenliang Li","doi":"10.1145/3336191.3371837","DOIUrl":"https://doi.org/10.1145/3336191.3371837","url":null,"abstract":"Mobility prediction, which is to predict where a user will arrive based on the user's historical mobility records, has attracted much attention. We argue that it is more useful to know not only where but also when a user will arrive next in many scenarios such as targeted advertising and taxi service. In this paper, we propose a novel context-aware deep model called DeepJMT for jointly performing mobility prediction (to know where) and time prediction (to know when). The DeepJMT model consists of (1) a hierarchical recurrent neural network (RNN) based sequential dependency encoder, which is more capable of capturing a user's mobility regularities and temporal patterns compared to vanilla RNN based models; (2) a spatial context extractor and a periodicity context extractor to extract location semantics and the user's periodicity, respectively; and (3) a co-attention based social & temporal context extractor which could extract the mobility and temporal evidence from social relationships. Experiments conducted on three real-world datasets show that DeepJMT outperforms the state-of-the-art mobility prediction and time prediction methods.","PeriodicalId":319008,"journal":{"name":"Proceedings of the 13th International Conference on Web Search and Data Mining","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116815872","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}
Feng Liu, Huifeng Guo, Xutao Li, Ruiming Tang, Yunming Ye, Xiuqiang He
The research of reinforcement learning (RL) based recommendation method has become a hot topic in recommendation community, due to the recent advance in interactive recommender systems. The existing RL recommendation approaches can be summarized into a unified framework with three components, namely embedding component (EC), state representation component (SRC) and policy component (PC). We find that EC cannot be nicely trained with the other two components simultaneously. Previous studies bypass the obstacle through a pre-training and fixing strategy, which makes their approaches unlike a real end-to-end fashion. More importantly, such pre-trained and fixed EC suffers from two inherent drawbacks: (1) Pre-trained and fixed embeddings are unable to model evolving preference of users and item correlations in the dynamic environment; (2) Pre-training is inconvenient in the industrial applications. To address the problem, in this paper, we propose an End-to-end Deep Reinforcement learning based Recommendation framework (EDRR). In this framework, a supervised learning signal is carefully designed for smoothing the update gradients to EC, and three incorporating ways are introduced and compared. To the best of our knowledge, we are the first to address the training compatibility between the three components in RL based recommendations. Extensive experiments are conducted on three real-world datasets, and the results demonstrate the proposed EDRR effectively achieves the end-to-end training purpose for both policy-based and value-based RL models, and delivers better performance than state-of-the-art methods.
{"title":"End-to-End Deep Reinforcement Learning based Recommendation with Supervised Embedding","authors":"Feng Liu, Huifeng Guo, Xutao Li, Ruiming Tang, Yunming Ye, Xiuqiang He","doi":"10.1145/3336191.3371858","DOIUrl":"https://doi.org/10.1145/3336191.3371858","url":null,"abstract":"The research of reinforcement learning (RL) based recommendation method has become a hot topic in recommendation community, due to the recent advance in interactive recommender systems. The existing RL recommendation approaches can be summarized into a unified framework with three components, namely embedding component (EC), state representation component (SRC) and policy component (PC). We find that EC cannot be nicely trained with the other two components simultaneously. Previous studies bypass the obstacle through a pre-training and fixing strategy, which makes their approaches unlike a real end-to-end fashion. More importantly, such pre-trained and fixed EC suffers from two inherent drawbacks: (1) Pre-trained and fixed embeddings are unable to model evolving preference of users and item correlations in the dynamic environment; (2) Pre-training is inconvenient in the industrial applications. To address the problem, in this paper, we propose an End-to-end Deep Reinforcement learning based Recommendation framework (EDRR). In this framework, a supervised learning signal is carefully designed for smoothing the update gradients to EC, and three incorporating ways are introduced and compared. To the best of our knowledge, we are the first to address the training compatibility between the three components in RL based recommendations. Extensive experiments are conducted on three real-world datasets, and the results demonstrate the proposed EDRR effectively achieves the end-to-end training purpose for both policy-based and value-based RL models, and delivers better performance than state-of-the-art methods.","PeriodicalId":319008,"journal":{"name":"Proceedings of the 13th International Conference on Web Search and Data Mining","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124216403","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}
Word embeddings, trained through models like skip-gram, have shown to be prone to capturing the biases from the training corpus, e.g. gender bias. Such biases are unwanted as they spill in downstream tasks, thus, leading to discriminatory behavior. In this work, we address the problem of prior sentiment associated with names in word embeddings where for a given name representation (e.g. "Smith"), a sentiment classifier will categorize it as either positive or negative. We propose DebiasEmb, a skip-gram based word embedding approach that, for a given oracle sentiment classification model, will debias the name representations, such that they cannot be associated with either positive or negative sentiment. Evaluation on standard word embedding benchmarks and a downstream analysis show that our approach is able to maintain a high quality of embeddings and at the same time mitigate sentiment bias in name embeddings.
{"title":"Debiasing Word Embeddings from Sentiment Associations in Names","authors":"C. Hube, Maximilian Idahl, B. Fetahu","doi":"10.1145/3336191.3371779","DOIUrl":"https://doi.org/10.1145/3336191.3371779","url":null,"abstract":"Word embeddings, trained through models like skip-gram, have shown to be prone to capturing the biases from the training corpus, e.g. gender bias. Such biases are unwanted as they spill in downstream tasks, thus, leading to discriminatory behavior. In this work, we address the problem of prior sentiment associated with names in word embeddings where for a given name representation (e.g. \"Smith\"), a sentiment classifier will categorize it as either positive or negative. We propose DebiasEmb, a skip-gram based word embedding approach that, for a given oracle sentiment classification model, will debias the name representations, such that they cannot be associated with either positive or negative sentiment. Evaluation on standard word embedding benchmarks and a downstream analysis show that our approach is able to maintain a high quality of embeddings and at the same time mitigate sentiment bias in name embeddings.","PeriodicalId":319008,"journal":{"name":"Proceedings of the 13th International Conference on Web Search and Data Mining","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124726550","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}
Zeyu Li, Wei Cheng, Yang Chen, Haifeng Chen, Wei Wang
Click-through rate (CTR) prediction is a critical task in online advertising and marketing. For this problem, existing approaches, with shallow or deep architectures, have three major drawbacks. First, they typically lack persuasive rationales to explain the outcomes of the models. Unexplainable predictions and recommendations may be difficult to validate and thus unreliable and untrustworthy. In many applications, inappropriate suggestions may even bring severe consequences. Second, existing approaches have poor efficiency in analyzing high-order feature interactions. Third, the polysemy of feature interactions in different semantic subspaces is largely ignored. In this paper, we propose InterHAt that employs a Transformer with multi-head self-attention for feature learning. On top of that, hierarchical attention layers are utilized for predicting CTR while simultaneously providing interpretable insights of the prediction results. InterHAt captures high-order feature interactions by an efficient attentional aggregation strategy with low computational complexity. Extensive experiments on four public real datasets and one synthetic dataset demonstrate the effectiveness and efficiency of InterHAt.
{"title":"Interpretable Click-Through Rate Prediction through Hierarchical Attention","authors":"Zeyu Li, Wei Cheng, Yang Chen, Haifeng Chen, Wei Wang","doi":"10.1145/3336191.3371785","DOIUrl":"https://doi.org/10.1145/3336191.3371785","url":null,"abstract":"Click-through rate (CTR) prediction is a critical task in online advertising and marketing. For this problem, existing approaches, with shallow or deep architectures, have three major drawbacks. First, they typically lack persuasive rationales to explain the outcomes of the models. Unexplainable predictions and recommendations may be difficult to validate and thus unreliable and untrustworthy. In many applications, inappropriate suggestions may even bring severe consequences. Second, existing approaches have poor efficiency in analyzing high-order feature interactions. Third, the polysemy of feature interactions in different semantic subspaces is largely ignored. In this paper, we propose InterHAt that employs a Transformer with multi-head self-attention for feature learning. On top of that, hierarchical attention layers are utilized for predicting CTR while simultaneously providing interpretable insights of the prediction results. InterHAt captures high-order feature interactions by an efficient attentional aggregation strategy with low computational complexity. Extensive experiments on four public real datasets and one synthetic dataset demonstrate the effectiveness and efficiency of InterHAt.","PeriodicalId":319008,"journal":{"name":"Proceedings of the 13th International Conference on Web Search and Data Mining","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126044474","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}
Natalia Silberstein, O. Somekh, Yair Koren, M. Aharon, Dror Porat, Avi Shahar, Tingyi Wu
Verizon Media native advertising (also known as Yahoo Gemini native) serves billions of ad impressions daily, reaching several hundreds of millions USD in revenue yearly. Although we strive to provide the best experience for our users, there will always be some users that dislike our ads in certain cases. To address these situations Gemini native platform provides an ad close mechanism that enables users to close ads that they dislike and also to provide a reasoning for their action. Surprisingly, users do care about their ad experience and their engagement with the ad close mechanism is quite significant. While the ad close rate (ACR) is lower than the click through rate (CTR), they are of the same order of magnitude, especially on Yahoo mail properties. Since ad close events indicate bad user experience caused mostly by poor ad quality, we would like to exploit the ad close signals to improve user experience and reduce the number of ad close events while maintaining a predefined total revenue loss. In this work we present our ad close mitigation (ACM) solution that penalizes ads with high closing likelihood, in our auctions. In particular, we use the ad close signal and other available features to predict the probability of an ad close event, and calculate the expected loss due to such event for using the true expected revenue in the auction. We show that this approach fundamentally changes the generalized second price (GSP) auction and provides incentive for advertisers to improve their ads' quality. Our solution was tested in both offline and large scale online settings, serving real Gemini native traffic. Results of the online experiment show that we are able to reduce the number of ad close events by more than 20%, while decreasing the revenue in less than 0.4%. In addition, we present a large scale analysis of the ad close signal that supports various design decisions and sheds light on ways the ad close mechanism affects different crowds.
{"title":"Ad Close Mitigation for Improved User Experience in Native Advertisements","authors":"Natalia Silberstein, O. Somekh, Yair Koren, M. Aharon, Dror Porat, Avi Shahar, Tingyi Wu","doi":"10.1145/3336191.3371798","DOIUrl":"https://doi.org/10.1145/3336191.3371798","url":null,"abstract":"Verizon Media native advertising (also known as Yahoo Gemini native) serves billions of ad impressions daily, reaching several hundreds of millions USD in revenue yearly. Although we strive to provide the best experience for our users, there will always be some users that dislike our ads in certain cases. To address these situations Gemini native platform provides an ad close mechanism that enables users to close ads that they dislike and also to provide a reasoning for their action. Surprisingly, users do care about their ad experience and their engagement with the ad close mechanism is quite significant. While the ad close rate (ACR) is lower than the click through rate (CTR), they are of the same order of magnitude, especially on Yahoo mail properties. Since ad close events indicate bad user experience caused mostly by poor ad quality, we would like to exploit the ad close signals to improve user experience and reduce the number of ad close events while maintaining a predefined total revenue loss. In this work we present our ad close mitigation (ACM) solution that penalizes ads with high closing likelihood, in our auctions. In particular, we use the ad close signal and other available features to predict the probability of an ad close event, and calculate the expected loss due to such event for using the true expected revenue in the auction. We show that this approach fundamentally changes the generalized second price (GSP) auction and provides incentive for advertisers to improve their ads' quality. Our solution was tested in both offline and large scale online settings, serving real Gemini native traffic. Results of the online experiment show that we are able to reduce the number of ad close events by more than 20%, while decreasing the revenue in less than 0.4%. In addition, we present a large scale analysis of the ad close signal that supports various design decisions and sheds light on ways the ad close mechanism affects different crowds.","PeriodicalId":319008,"journal":{"name":"Proceedings of the 13th International Conference on Web Search and Data Mining","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131009432","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}
Online platforms such as LinkedIn or specialized platforms such as Glassdoor are widely used by job seekers before applying for the job. These web platforms have rating and reviews about employer and jobs. Hence a job seeker do online search for the employer, before applying for the job. They try to find if the employer and job is good for them or not, what are the pros and cons of working there etc. Therefore, these reviews and ratings have an impact on job seekers decision as it portrays the pros and cons of working in a particular firm. Hence, the main objective of this study is main objective of this study is to find how the job seekers search for online employer reviews and the impact of these reviews on employer attractiveness and job pursuit intention. The other objective is to find the most crucial job factors that are given priority by the employee. For this, the study is proposed to be conducted in two stages, first, collecting data from the website Glassdoor, having 600000 companies' reviews. In the second stage, conducting an experimental study to examine the influence of job attributes (high vs. low) and employer rating (high vs. low) on job choice and employer attractiveness.
{"title":"Impact of Online Job Search and Job Reviews on Job Decision","authors":"Faiz Ahamad","doi":"10.1145/3336191.3372184","DOIUrl":"https://doi.org/10.1145/3336191.3372184","url":null,"abstract":"Online platforms such as LinkedIn or specialized platforms such as Glassdoor are widely used by job seekers before applying for the job. These web platforms have rating and reviews about employer and jobs. Hence a job seeker do online search for the employer, before applying for the job. They try to find if the employer and job is good for them or not, what are the pros and cons of working there etc. Therefore, these reviews and ratings have an impact on job seekers decision as it portrays the pros and cons of working in a particular firm. Hence, the main objective of this study is main objective of this study is to find how the job seekers search for online employer reviews and the impact of these reviews on employer attractiveness and job pursuit intention. The other objective is to find the most crucial job factors that are given priority by the employee. For this, the study is proposed to be conducted in two stages, first, collecting data from the website Glassdoor, having 600000 companies' reviews. In the second stage, conducting an experimental study to examine the influence of job attributes (high vs. low) and employer rating (high vs. low) on job choice and employer attractiveness.","PeriodicalId":319008,"journal":{"name":"Proceedings of the 13th International Conference on Web Search and Data Mining","volume":"143 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128397712","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}
Recently, plenty of neural network based recommendation models have demonstrated their strength in modeling complicated relationships between heterogeneous objects (i.e., users and items). However, the applications of these fine trained recommendation models are limited to the off-line manner or the re-ranking procedure (on a pre-filtered small subset of items), due to their time-consuming computations. Fast item ranking under learned neural network based ranking measures is largely still an open question. In this paper, we formulate ranking under neural network based measures as a generic ranking task, Optimal Binary Function Search (OBFS), which does not make strong assumptions for the ranking measures. We first analyze limitations of existing fast ranking methods (e.g., ANN search) and explain why they are not applicable for OBFS. Further, we propose a flexible graph-based solution for it, Binary Function Search on Graph (BFSG). It can achieve approximate optimal efficiently, with accessible conditions. Experiments demonstrate effectiveness and efficiency of the proposed method, in fast item ranking under typical neural network based measures.
{"title":"Fast Item Ranking under Neural Network based Measures","authors":"Shulong Tan, Zhixin Zhou, Zhao-Ying Xu, Ping Li","doi":"10.1145/3336191.3371830","DOIUrl":"https://doi.org/10.1145/3336191.3371830","url":null,"abstract":"Recently, plenty of neural network based recommendation models have demonstrated their strength in modeling complicated relationships between heterogeneous objects (i.e., users and items). However, the applications of these fine trained recommendation models are limited to the off-line manner or the re-ranking procedure (on a pre-filtered small subset of items), due to their time-consuming computations. Fast item ranking under learned neural network based ranking measures is largely still an open question. In this paper, we formulate ranking under neural network based measures as a generic ranking task, Optimal Binary Function Search (OBFS), which does not make strong assumptions for the ranking measures. We first analyze limitations of existing fast ranking methods (e.g., ANN search) and explain why they are not applicable for OBFS. Further, we propose a flexible graph-based solution for it, Binary Function Search on Graph (BFSG). It can achieve approximate optimal efficiently, with accessible conditions. Experiments demonstrate effectiveness and efficiency of the proposed method, in fast item ranking under typical neural network based measures.","PeriodicalId":319008,"journal":{"name":"Proceedings of the 13th International Conference on Web Search and Data Mining","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127942032","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}
Sequential recommender systems seek to exploit the order of users' interactions, in order to predict their next action based on the context of what they have done recently. Traditionally, Markov Chains(MCs), and more recently Recurrent Neural Networks (RNNs) and Self Attention (SA) have proliferated due to their ability to capture the dynamics of sequential patterns. However a simplifying assumption made by most of these models is to regard interaction histories as ordered sequences, without regard for the time intervals between each interaction (i.e., they model the time-order but not the actual timestamp). In this paper, we seek to explicitly model the timestamps of interactions within a sequential modeling framework to explore the influence of different time intervals on next item prediction. We propose TiSASRec (Time Interval aware Self-attention based sequential recommendation), which models both the absolute positions of items as well as the time intervals between them in a sequence. Extensive empirical studies show the features of TiSASRec under different settings and compare the performance of self-attention with different positional encodings. Furthermore, experimental results show that our method outperforms various state-of-the-art sequential models on both sparse and dense datasets and different evaluation metrics.
{"title":"Time Interval Aware Self-Attention for Sequential Recommendation","authors":"Jiacheng Li, Yujie Wang, Julian McAuley","doi":"10.1145/3336191.3371786","DOIUrl":"https://doi.org/10.1145/3336191.3371786","url":null,"abstract":"Sequential recommender systems seek to exploit the order of users' interactions, in order to predict their next action based on the context of what they have done recently. Traditionally, Markov Chains(MCs), and more recently Recurrent Neural Networks (RNNs) and Self Attention (SA) have proliferated due to their ability to capture the dynamics of sequential patterns. However a simplifying assumption made by most of these models is to regard interaction histories as ordered sequences, without regard for the time intervals between each interaction (i.e., they model the time-order but not the actual timestamp). In this paper, we seek to explicitly model the timestamps of interactions within a sequential modeling framework to explore the influence of different time intervals on next item prediction. We propose TiSASRec (Time Interval aware Self-attention based sequential recommendation), which models both the absolute positions of items as well as the time intervals between them in a sequence. Extensive empirical studies show the features of TiSASRec under different settings and compare the performance of self-attention with different positional encodings. Furthermore, experimental results show that our method outperforms various state-of-the-art sequential models on both sparse and dense datasets and different evaluation metrics.","PeriodicalId":319008,"journal":{"name":"Proceedings of the 13th International Conference on Web Search and Data Mining","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128274823","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：