In large-scale recommendation systems like LinkedIn’s, the retrieval stage is critical for narrowing billions of potential candidates to a manageable subset for ranking. LinkedIn's feed now serves suggested content based on the topical interests of members, where 2000 candidates are retrieved from several million candidates with a latency budget of a few milliseconds and inbound QPS of several thousand per second. This paper presents a novel retrieval approach that fine tunes a large causal language model (Meta’s LLaMA 3) as a dual encoder to generate high quality embeddings for both users (members) and content (items), using only textual input. We describe the end to end pipeline, including prompt design for embedding generation, techniques for fine tuning at LinkedIn scale, and infrastructure for low latency, cost effective online serving. We share our findings on how quantizing numerical features in the prompt enables the information getting encoded in the embedding facilitating greater alignment between the retrieval and ranking layer. The system was evaluated using offline metrics and an online A/B test, which showed substantial improvements in member engagement. We observed significant gains among newer members, who often lack strong network connections, indicating that high-quality suggested content aids retention. This work demonstrates how generative language models can be effectively adapted for real time, high throughput retrieval in industrial applications.

A post embedding (representation of text in embedding space that effectively captures semantic meaning) is a foundational component of LinkedIn that is consumed by product surfaces in retrieval and ranking (e.g., ranking posts in the feed or video tab). This paper presents the post embeddings used at LinkedIn, where a pre-trained transformer-based large language model (LLM) is taken as input and fine-tuned using multi-task learning across a diverse set of semantic labeling tasks. We observe positive transfer, leading to improved performance across all tasks, compared to training them independently. The generated post embeddings outperform baseline models in zero-shot learning, demonstrating its potential for broader applicability. Furthermore, the generated post embeddings' performance surpasses that of OpenAI's ADA-001 and ADA-002 embeddings on LinkedIn specific datasets and tasks. We also describe the offline evaluation methodology and the deployment to our near-line infrastructure, which makes the post embedding available for use within minutes of post creation for any downstream application. We present how the embeddings were applied in the Feed product surface, in both ranking and retrieval stages, and showcase the real world online impact to demonstrate the superior performance of these embeddings. Finally, we also share the results of applying the embeddings to the retrieval system of our video ranking product surface in LinkedIn. These embeddings have been battle-tested in production at LinkedIn for over two years, consistently powering multiple products.

In this paper, we present LiGNN, a deployed large-scale Graph Neural Networks (GNNs) Framework. We share our insight on developing and deployment of GNNs at large scale at LinkedIn. We present a set of algorithmic improvements to the quality of GNN representation learning including temporal graph architectures with long term losses, effective cold start solutions via graph densification, ID embeddings and multi-hop neighbor sampling. We explain how we built and sped up by 7x our large-scale training on LinkedIn graphs with adaptive sampling of neighbors, grouping and slicing of training data batches, specialized shared-memory queue and local gradient optimization. We summarize our deployment lessons and learnings gathered from A/B test experiments. The techniques presented in this work have contributed to an approximate relative improvements of 1% of Job application hearing back rate, 2% Ads CTR lift, 0.5% of Feed engaged daily active users, 0.2% session lift and 0.1% weekly active user lift from people recommendation. We believe that this work can provide practical solutions and insights for engineers who are interested in applying Graph neural networks at large scale.

We present LiRank, a large-scale ranking framework at LinkedIn that brings to production state-of-the-art modeling architectures and optimization methods. We unveil several modeling improvements, including Residual DCN, which adds attention and residual connections to the famous DCNv2 architecture. We share insights into combining and tuning SOTA architectures to create a unified model, including Dense Gating, Transformers and Residual DCN. We also propose novel techniques for calibration and describe how we productionalized deep learning based explore/exploit methods.

Social networks and content publishing platforms have newsfeed applications, which show both organic content to drive engagement, and ads to drive revenue. This paper focuses on the problem of ads allocation in a newsfeed to achieve an optimal balance of revenue and engagement. To the best of our knowledge, we are the first to report practical solutions to this business-critical and popular problem in industry.

Cloud applications have increasingly come to rely on distributed storage systems that hide the complexity of handling network and node failures behind simple, data-centric interfaces (such as PUTs and GETs on key-value pairs). While these interfaces are very easy to use, the application is completely oblivious to the location of its data in the network; as a result, it has no way to optimize the placement of data or computation. In this paper, we propose exposing the network location of data to applications. The primary challenge is that data does not usually exist at a single point in the network; it can be striped, replicated, cached and coded across different locations, in arbitrary ways that vary across storage systems. For example, an item that is synchronously mirrored in both Seattle and London will appear equally far from both locations for writes, but equally close to both locations for reads. Accordingly, we describe Contour, a system that allows applications to query and manipulate the location of data without requiring them to be aware of the physical machines storing the data, the replication protocols used or the underlying network topology.

The use of cellular data networks is increasingly popular due to the widespread deployment of 3G technologies and the rapid adoption of smartphones, such as iPhone and GPhone. Besides email and web browsing, a variety of network applications are now available, rendering smartphones potentially useful substitutes for their desktop counterparts. Nevertheless, the performance of smartphone applications in the wild is still poorly understood due to a lack of systematic measurement methodology.

Clustering is used commonly in ad hoc networks for hierarchical routing. Size-bounded clustering has been proposed to restrict the maximum size of a cluster so that the routing load, and hence the energy drain, on the clusterhead is bounded. However, all the existing size-bounded clustering algorithms take the size bound as the number of nodes in the cluster. This approach may still result in high routing load on a clusterhead if the traffic rate of the nodes in the cluster is high. In this paper, we propose a simple metric based on average traffic rates of nodes for size-bounded clustering that reflects the actual routing load on a clusterhead. We present a distributed clustering algorithm that bounds the cluster size in terms of this metric, and also reduces the total energy spent in sending all the packets. Detailed simulation results are presented to show that the protocol performs significantly better than some other size-bounded clustering schemes.