Knowledge-adaptive contrastive learning for recommendation
By jointly modeling user-item interactions and knowledge graph (KG) information, KG-based
recommender systems have shown their superiority in alleviating data sparsity and cold start …
recommender systems have shown their superiority in alleviating data sparsity and cold start …
Addressing confounding feature issue for causal recommendation
In recommender systems, some features directly affect whether an interaction would
happen, making the happened interactions not necessarily indicate user preference. For …
happen, making the happened interactions not necessarily indicate user preference. For …
Exploring false hard negative sample in cross-domain recommendation
Negative Sampling in recommendation aims to capture informative negative instances for
the sparse user-item interactions to improve the performance. Conventional negative …
the sparse user-item interactions to improve the performance. Conventional negative …
What functions can Graph Neural Networks compute on random graphs? The role of Positional Encoding
We aim to deepen the theoretical understanding of Graph Neural Networks (GNNs) on large
graphs, with a focus on their expressive power. Existing analyses relate this notion to the …
graphs, with a focus on their expressive power. Existing analyses relate this notion to the …
Elastic structural analysis based on graph neural network without labeled data
LH Song, C Wang, JS Fan… - Computer‐Aided Civil and …, 2023 - Wiley Online Library
Artificial intelligence is gaining increasing popularity in structural analysis. However, at the
structural system level, the appropriateness of data representation, the paucity of data, and …
structural system level, the appropriateness of data representation, the paucity of data, and …
Influences of information sharing and online recommendations in a supply chain: reselling versus agency selling
X Chen, B Li, W Chen, S Wu - Annals of Operations Research, 2023 - Springer
This paper investigates the effects of reselling and agency contracts on the platform's
incentive to share information under two scenarios, ie, the recommendation scenario and …
incentive to share information under two scenarios, ie, the recommendation scenario and …
Bridging the Gap between Relational {OLTP} and Graph-based {OLAP}
Recently, many applications have required the ability to perform dynamic graph analytical
processing (GAP) tasks on the datasets generated by relational OLTP in real time. To meet …
processing (GAP) tasks on the datasets generated by relational OLTP in real time. To meet …
Elpis: Graph-based similarity search for scalable data science
I Azizi, K Echihabi, T Palpanas - Proceedings of the VLDB Endowment, 2023 - dl.acm.org
The recent popularity of learned embeddings has fueled the growth of massive collections of
high-dimensional (high-d) vectors that model complex data. Finding similar vectors in these …
high-dimensional (high-d) vectors that model complex data. Finding similar vectors in these …
Riding a bicycle while building its wheels: the process of machine learning-based capability development and IT-business alignment practices
Purpose Recent advancements in Artificial Intelligence (AI) and, at its core, Machine
Learning (ML) offer opportunities for organizations to develop new or enhance existing …
Learning (ML) offer opportunities for organizations to develop new or enhance existing …
Graphguard: Detecting and counteracting training data misuse in graph neural networks
The emergence of Graph Neural Networks (GNNs) in graph data analysis and their
deployment on Machine Learning as a Service platforms have raised critical concerns about …
deployment on Machine Learning as a Service platforms have raised critical concerns about …