LinkedIn, one of the world's largest platforms for professional networking and job seeking, encounters various modeling challenges in building recommendation systems for its job matching product, including cold-start, filter bubbles, and biases affecting candidate-job matching. To address these, we developed the STAR (Signal integration for Talent And Recruiters) system, leveraging the combined strengths of Large Language Models (LLMs) and Graph Neural Networks (GNNs). LLMs excel at understanding textual data, such as member profiles and job postings, while GNNs capture intricate relationships and mitigate cold-start issues through network effects. STAR integrates diverse signals by uniting LLM and GNN capabilities with industrial-scale paradigms including adaptive sampling and version management. It provides an end-to-end solution for developing and deploying embeddings in large-scale recommender systems. Our key contributions include a robust methodology for building embeddings in industrial applications, a scalable GNN-LLM integration for high-performing recommendations, and practical insights for real-world model deployment.

Accurate projection of terms in free-text queries onto structured entity representations is one of the fundamental problems in entity retrieval from knowledge graphs. In this paper, we demonstrate that existing retrieval models for ad-hoc structured and unstructured document retrieval fall short of addressing this problem, due to their rigid assumptions. According to these assumptions, either all query concepts of the same type (unigrams and bigrams) are projected onto the fields of entity representations with identical weights or such projection is determined based only on one simple statistic, which makes it sensitive to data sparsity. To address this issue, we propose the Parametrized Fielded Sequential Dependence Model (PFSDM) and the Parametrized Fielded Full Dependence Model (PFFDM), two novel models for entity retrieval from knowledge graphs, which infer the user's intent behind each individual query concept by dynamically estimating its projection onto the fields of structured entity representations based on a small number of statistical and linguistic features. Experimental results obtained on several publicly available benchmarks indicate that PFSDM and PFFDM consistently outperform state-of-the-art retrieval models for the task of entity retrieval from knowledge graph.

Previously proposed approaches to ad-hoc entity retrieval in the Web of Data (ERWD) used multi-fielded representation of entities and relied on standard unigram bag-of-words retrieval models. Although retrieval models incorporating term dependencies have been shown to be significantly more effective than the unigram bag-of-words ones for ad hoc document retrieval, it is not known whether accounting for term dependencies can improve retrieval from the Web of Data. In this work, we propose a novel retrieval model that incorporates term dependencies into structured document retrieval and apply it to the task of ERWD. In the proposed model, the document field weights and the relative importance of unigrams and bigrams are optimized with respect to the target retrieval metric using a learning-to-rank method. Experiments on a publicly available benchmark indicate significant improvement of the accuracy of retrieval results by the proposed model over state-of-the-art retrieval models for ERWD.

Entity ranking has become increasingly important, both for retrieving structured entities and for use in general web search applications. The most common format for linked data, RDF graphs, provide extensive semantic structure via predicate links. While the semantic information is potentially valuable for effective search, the resulting adjacency matrices are often sparse, which introduces challenges for representation and ranking. In this paper, we propose a principled and scalable approach for integrating of latent semantic information into a learning-to-rank model, by combining compact representation of semantic similarity, achieved by using a modified algorithm for tensor factorization, with explicit entity information. Our experiments show that the resulting ranking model scales well to the graphs with millions of entities, and outperforms the state-of-the-art baseline on realistic Yahoo! SemSearch Challenge data sets.