Cross-domain collaboration recommendation

By Jie Tang, Sen Wu, Jimeng Sun, Hang Su. Knowledge Discovery and Data Mining, 2012

344 citations recorded by the source corpus.

Subfields: Information Systems, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/ef9a064ea9c4735895d59f51032ce3add2c8737c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Information Systems

In Statistical and Nonlinear Physics

Citations in the corpus

A Multi-View Deep Learning Approach for Cross Domain User Modeling in Recommendation Systems (2015, methodology): “To further show the strength of our approach in modeling cross-domain users, we perform a set of experiments on the public data 2 by the authors in [28].”
Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders (2024, neutral): “Early approaches relied on keyword tagging (Mooney and Roy, 2000; Wang and Blei, 2011; Tang et al., 2012), which were largely heuristic and discarded substantial semantic information.”
Cross-domain Recommendation Without Sharing User-relevant Data (2019, positive): “The task of leveraging auxiliary data from other domains to improve recommendation quality of the target domain is known as the cross-domain recommendation [1, 10, 15, 32, 35, 43].”
Cross-domain Recommendation via Deep Domain Adaptation (2018, background): “While this approach allows the application of single-domain methods, such features are often hard to obtain as users often hesitate to reveal their profiles due to privacy concerns.”
Text Is All You Need: Learning Language Representations for Sequential Recommendation (2023, methodology): “In this section, we present Recformer which can learn language representations for sequential recommendation and effectively transfer and generalize to new recommendation scenarios.”
Ieee Transactions on Knowledge and Data Engineering, Manuscropt Id 1 Social Recommendation with Cross-domain Transferable Knowledge (positive): “Recommender systems benefit from new information that goes beyond the user-item matrix [16][17][18][19].”
LCARS: a location-content-aware recommender system (2013, methodology): “Following the studies [26, 25], we use collapsed Gibbs sampling to obtain samples of the hidden variable assignment and to estimate unknown parameters {θ, θ′, φ, φ′, λ}”
Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation (2019, background): “or books). MKR can also maintain a decent performance in sparse scenarios. Contribution It is worth noticing that the problem studied in this paper can also be modelled as cross-domain recommendation [26] or transfer learning [21], since we care more about the performance of recommendation task. How”
Simplicial closure and higher-order link prediction (2018, background): “Link prediction also has a number of direct applications that cut across disciplines, including predicting friendships in social networks (38), inferring new relationships between genes and diseases (39), and suggesting novel connections in the scientific community (40).”
Multistakeholder recommendation: Survey and research directions (2020, background): “Other reciprocal recommendation domains include job seeking (Rodriguez et al. 2012b), peer-to-peer “sharing economy” recommendation (such as AirBnB, Uber, and others), online advertising (Iyer et al. 2005), and scientiﬁc collaboration (Lopes et al. 2010; Tang et al. 2012).”
Link prediction in social networks: the state-of-the-art (2014, methodology): “Through analyzing the cross-domain collaboration networks, Tang et al. proposed the Cross-domain Topic Learning (CTL) model [110] to solve above challenges: (1) for handling sparse connections, CTL consolidates the existing cross-domain collaborations through topic layers instead of at author…”
Inferring anchor links across multiple heterogeneous social networks (2013, background): “In addition, another line of research works study the link prediction problems on multiple networks or domains [5, 7, 20, 24, 21].”
Cross-Domain Recommendation via Cluster-Level Latent Factor Model (2013, background): “[15] proposed the cross-domain topic learning model to predict the cross-domain collaborations through topic layers instead of at author layers, which alleviated the sparseness issue.”