the proceedings contain 109 papers. the topics discussed include: from search to research: direct answers, perspectives and dialog;scalable algorithms in the age of big data and network sciences: characterization, pri...
ISBN:
(纸本)9781450355810
the proceedings contain 109 papers. the topics discussed include: from search to research: direct answers, perspectives and dialog;scalable algorithms in the age of big data and network sciences: characterization, primitives, and techniques;conversations, machine learning and privacy: linkedin's path towards transforming interaction with its members;WSDM Cup 2018: music recommendation and churn prediction;deep neural architecture for multi-modal retrieval based on joint embedding space for text and images;sequential recommendation with user memory networks;latent cross: making use of context in recurrent recommender systems;and can you trust the trend? discovering Simpson's paradoxes in social data.
the proceedings contain 150 papers. the topics discussed include: graph disentangle causal model: enhancing causal inference in networked observational data;CIMAGE: exploiting the conditional independence in masked gr...
ISBN:
(纸本)9798400713293
the proceedings contain 150 papers. the topics discussed include: graph disentangle causal model: enhancing causal inference in networked observational data;CIMAGE: exploiting the conditional independence in masked graph auto-encoders;a sublinear algorithm for approximate shortest paths in large networks;POLARIS: sampling from the multigraph configuration model with prescribed color assortativity;DiffGraph: heterogeneous graph diffusion model;mitigating overfitting in graph neural networks via feature and hyperplane perturbation;dynamic graph transformer with correlated spatial-temporal positional encoding;S-Diff: an anisotropic diffusion model for collaborative filtering in spectral domain;hyperdimensional representation learning for node classification and link prediction;prospective multi-graph cohesion for multivariate time series anomaly detection;and a contrastive framework with user, item and review alignment for recommendation.
the proceedings contain 78 papers. the topics discussed include: improving the efficiency of multi-site websearch engines;a self-adapting latency/power tradeoff model for replicated search engines;heterogeneous graph...
ISBN:
(纸本)9781450323512
the proceedings contain 78 papers. the topics discussed include: improving the efficiency of multi-site websearch engines;a self-adapting latency/power tradeoff model for replicated search engines;heterogeneous graph-based intent learning with queries, web pages and Wikipedia concepts;exploiting user disagreement for websearch evaluation: an experimental approach;improving search relevance for short queries in community question answering;struggling or exploring? disambiguating long search sessions;democracy is good for ranking: towards multi-view rank learning and adaptation in websearch;relative confidence sampling for efficient on-line ranker evaluation;and search engine click spam detection based on bipartite graph propagation.
the proceedings contain 86 papers. the topics discussed include: exploiting statistical and relational information on the web and in social media;web retrieval: the role of users;personalizing websearch using long te...
ISBN:
(纸本)9781450304931
the proceedings contain 86 papers. the topics discussed include: exploiting statistical and relational information on the web and in social media;web retrieval: the role of users;personalizing websearch using long term browsing history;identifying topical authorities in microblogs;correcting for missing data in information cascades;a comparative analysis of cascade measures for novelty and diversity;understanding and predicting personal navigation;quality-biased ranking of web documents;ranking from pairs and triplets: information quality, evaluation methods and query complexity;we feel fine and searching the emotional web;on the selection of tags for tag clouds;batch query processing for websearch engines;detecting duplicate web documents using clickthrough data;understanding temporal query dynamics;patterns of temporal variation in online media;and using graded-relevance metrics for evaluating community QA answer selection.
the proceedings contain 93 papers. the topics discussed include: information-theoretic measures of influence based on content dynamics;characterizing and curating conversation threads: expansion, focus, volume, re-ent...
ISBN:
(纸本)9781450318693
the proceedings contain 93 papers. the topics discussed include: information-theoretic measures of influence based on content dynamics;characterizing and curating conversation threads: expansion, focus, volume, re-entry;structure and dynamics of information pathways in online media;patent partner recommendation in enterprise social networks;exploiting homophily effect for trust prediction;efficient and effective retrieval using selective pruning;document selection for tiered indexing in commerce search;quasi-succinct indices;identifying users' topical tasks in websearch;differences in search engine evaluations between query owners and non-owners;optimizing top-k document retrieval strategies for block-max indexes;improving the sensitivity of online controlled experiments by utilizing pre-experiment data;and playing by the rules: mining query associations to predict search performance.
the proceedings contain 51 papers. the topics discussed include: new directions in recommender systems;delayed-dynamic-selective (DDS) prediction for reducing extreme tail latency in websearch;engagement periodicity ...
ISBN:
(纸本)9781450333177
the proceedings contain 51 papers. the topics discussed include: new directions in recommender systems;delayed-dynamic-selective (DDS) prediction for reducing extreme tail latency in websearch;engagement periodicity in search engine usage: analysis and its application to search quality evaluation;optimal space-time tradeoffs for inverted indexes;understanding and predicting graded search satisfaction;robust tree-based causal inference for complex ad effectiveness analysis;the power of random neighbors in social networks;negative link prediction in social media;sarcasm detection on Twitter: a behavioral modeling approach;modeling and predicting retweeting dynamics on microblogging platforms;on integrating network and community discovery;and on the accuracy of hyper-local geotagging of social media content.
the proceedings contain 81 papers. the topics discussed include: spatially-aware indexing for image object retrieval;Auralist: introducing serendipity into music recommendation;beyond co-occurrence: discovering and vi...
ISBN:
(纸本)9781450307475
the proceedings contain 81 papers. the topics discussed include: spatially-aware indexing for image object retrieval;Auralist: introducing serendipity into music recommendation;beyond co-occurrence: discovering and visualizing tag relationships from geo-spatial and temporal similarities;overcoming browser cookie churn with clustering;of hammers and nails: an empirical comparison of three paradigms for processing large graphs;mining slang and urban opinion words and phrases from cQA services: an optimization approach;characterizing web content, user interests, and search behavior by reading level and topic;selecting actions for resource-bounded information extraction using reinforcement learning;overlapping clusters for distributed computation;personalized click model through collaborative filtering;extracting search-focused key N-grams for relevance ranking in websearch;and tapping into knowledge base for concept feedback: leveraging ConceptNet to improve search results for difficult queries.
the proceedings contain 115 papers. the topics discussed include: fast dictionary-based compression for inverted indexes;joint optimization of cascade ranking models;WassRank: listwise document ranking using optimal t...
ISBN:
(纸本)9781450359405
the proceedings contain 115 papers. the topics discussed include: fast dictionary-based compression for inverted indexes;joint optimization of cascade ranking models;WassRank: listwise document ranking using optimal transport theory;integrating local context and global cohesiveness for open information extraction;knowledge graph enhanced community detection and characterization;representation interpretation with spatial encoding and multimodal analytics;interaction embeddings for prediction and explanation in knowledge graphs;knowledge graph embedding based question answering;relevance search over schema-rich knowledge graphs;a state transition model for mobile notifications via survival analysis;and clustered monotone transforms for rating factorization.
the proceedings contain 168 papers. the topics discussed include: domain level interpretability: interpreting black-box model with domain-specific embedding;ranking with long-term constraints;LMBot: distilling graph k...
ISBN:
(纸本)9798400703713
the proceedings contain 168 papers. the topics discussed include: domain level interpretability: interpreting black-box model with domain-specific embedding;ranking with long-term constraints;LMBot: distilling graph knowledge into language model for graph-less deployment in twitter bot detection;to copy, or not to copy;that is a critical issue of the output Softmax layer in neural sequential recommenders;PEFA: parameter-free adapters for large-scale embedding-based retrieval models;empathetic response generation with relation-aware commonsense knowledge;professional network matters: connections empower person-job fit;towards mitigating dimensional collapse of representations in collaborative filtering;exploiting duality in open information extraction with predicate prompt;and guardian: guarding against gradient leakage with provable defense for federated learning.
the proceedings contain 79 papers. the topics discussed include: who will reply to/retweet this tweet? the dynamics of intimacy from online social interactions;cross-modality consistent regression for joint visual-tex...
ISBN:
(纸本)9781450337168
the proceedings contain 79 papers. the topics discussed include: who will reply to/retweet this tweet? the dynamics of intimacy from online social interactions;cross-modality consistent regression for joint visual-textual sentiment analysis of social multimedia;CCCF: improving collaborative filtering via scalable user-item co-clustering;on the efficiency of the information networks in social media;understanding and measuring user engagement and entertainment in online news reading;to suggest, or not to suggest for queries with diverse intents: optimizing search result presentation;collaborative denoising auto-encoders for top-n recommender systems;personalized Pagerank estimation and search: a bidirectional approach;quality management in crowdsourcing using gold judges behavior;modeling check-in preferences with multidimensional knowledge: a MiniMax entropy approach;hierarchical label propagation and discovery for machine generated email;and multileave gradient descent for fast online learning to rank.
暂无评论