Entity Linking, the task of mapping ambiguous Named Entities to unique identifiers in a knowledge base, is a cornerstone of multiple Information Retrieval and Text Analysis systems. So far, no single entity linking algorithm has been able to offer the accuracy and scalability required to deal with the ever-increasing amount of data in the web and become a de-facto standard.In this paper, we propose a framework for entity linking that leverages graph embeddings to perform collective disambiguation. This framework is modular as it supports pluggable algorithms for embedding generation and candidate ranking. With our framework, we implement and evaluate a reference pipeline that uses DBpedia as knowledge base and leverages specific algorithms for fast candidate search and high-performance state-space search optimization. Compared to existing solutions, our approach offers state-of-the-art accuracy on a variety of datasets without any supervised training and provides real-time execution even when processing documents with dozens of Named Entities. Lastly, the flexibility of our framework allows adapting to a multitude of scenarios by balancing accuracy and execution time.

Federated Learning (FL) is very appealing for its privacy benefits: essentially, a global model is trained with updates computed on mobile devices while keeping the data of users local. Standard FL infrastructures are however designed to have no energy or performance impact on mobile devices, and are therefore not suitable for applications that require frequent ( online ) model updates, such as news recommenders. This paper presents FLeet , the first Online FL system, acting as a middleware between the Android OS and the machine learning application. FLeet combines the privacy of Standard FL with the precision of online learning thanks to two core components: (i) I-Prof , a new lightweight profiler that predicts and controls the impact of learning tasks on mobile devices, and (ii) AdaSGD , a new adaptive learning algorithm that is resilient to delayed updates. Our extensive evaluation shows that Online FL, as implemented by FLeet , can deliver a 2.3 × quality boost compared to Standard FL, while only consuming 0.036% of the battery per day. I-Prof can accurately control the impact of learning tasks by improving the prediction accuracy by up to 3.6 × in terms of computation time, and by up to 19 × in terms of energy. AdaSGD outperforms alternative FL approaches by 18.4% in terms of convergence speed on heterogeneous data.

No abstract

Similarity computations are crucial in various web activities like advertisements, search or trust-distrust predictions. These similarities often vary with time as product perception and popularity constantly change with users' evolving inclination. The huge volume of user-generated data typically results in heavyweight computations for even a single similarity update. We present I-SIM, a novel similarity metric that enables lightweight similarity computations in an incremental and temporal manner. Incrementality enables updates with low latency whereas temporality captures users' evolving inclination. The main idea behind I-SIM is to disintegrate the similarity metric into mutually independent time-aware factors which can be updated incrementally. We illustrate the efficacy of I-SIM through a novel recommender (SWIFT) as well as through a trust-distrust predictor in Online Social Networks (I-TRUST). We experimentally show that I-SIM enables fast and accurate predictions in an energy-efficient manner.

The upsurge in the number of web users over the last two decades has resulted in a significant growth of online information. This information growth calls for recommenders that personalize the information proposed to each individual user. Nevertheless, personalization also opens major privacy concerns. This paper presents D 2 P , a novel protocol that ensures a strong form of differential privacy, which we call distance-based differential privacy, and which is particularly well suited to recommenders. D 2 P avoids revealing exact user profiles by creating altered profiles where each item is replaced with another one at some distance. We evaluate D 2 P analytically and experimentally on MovieLens and Jester datasets and compare it with other private and non-private recommenders.