Federated learning (FL) is a popular way of edge computing that doesn't compromise users' privacy. Current FL paradigms assume that data only resides on the edge, while cloud servers only perform model averaging. However, in real-life situations such as recommender systems, the cloud server has the ability to store historical and interactive features. In this paper, our proposed Edge-Cloud Collaborative Knowledge Transfer Framework (ECCT) bridges the gap between the edge and cloud, enabling bi-directional knowledge transfer between both, sharing feature embeddings and prediction logits. ECCT consolidates various benefits, including enhancing personalization, enabling model heterogeneity, tolerating training asynchronization, and relieving communication burdens. Extensive experiments on public and industrial datasets demonstrate ECCT's effectiveness and potential for use in academia and industry.

Music streaming services often aim to recommend songs for users to extend the playlists they have created on these services. However, extending playlists while preserving their musical characteristics and matching user preferences remains a challenging task, commonly referred to as Automatic Playlist Continuation (APC). Besides, while these services often need to select the best songs to recommend in real-time and among large catalogs with millions of candidates, recent research on APC mainly focused on models with few scalability guarantees and evaluated on relatively small datasets. In this paper, we introduce a general framework to build scalable yet effective APC models for large-scale applications. Based on a represent-then-aggregate strategy, it ensures scalability by design while remaining flexible enough to incorporate a wide range of representation learning and sequence modeling techniques, e.g., based on Transformers. We demonstrate the relevance of this framework through in-depth experimental validation on Spotify's Million Playlist Dataset (MPD), the largest public dataset for APC. We also describe how, in 2022, we successfully leveraged this framework to improve APC in production on Deezer. We report results from a large-scale online A/B test on this service, emphasizing the practical impact of our approach in such a real-world application.

Numerous car companies are trying their hands at digital assistants, but Mini is planning something more... characterful. The automaker has unveiled Spike, an English Bulldog-inspired helper coming to future Mini models. While his exact functionality is still unknown, he'll walk you through the "operating concept" of a given car and is meant to foster an "emotional connection." We suspect this pup won't seem so loveable when you're in a hurry, but it might beat the personality-free assistants from other makes. Spike will make his debut in the cabin of the Mini Concept Aceman at the Shanghai auto show beginning April 18th.

Digital workers are intelligent software bots that automate everyday business processes like data entry, invoicing, or system queries. They will take over many repetitive and mundane tasks, creating new opportunities for businesses and workers. People aren’t just more productive when they work with digital workers; they are also happier. Automation is the future of work. Already, 74% of businesses use automation to drive efficiency and navigate the convergence of problems we face at the moment: the ongoing aftershocks of a global pandemic, raging inflation, and increasingly complex regulations. But the leaders among them will embrace and deploy digital workers to partner with…

Abstract--Graph mining algorithms have been playing a significant role in myriad fields over the years. However, despite their promising performance on various graph analytical tasks, most of these algorithms lack fairness considerations. As a consequence, they could lead to discrimination towards certain populations when exploited in human-centered applications. Recently, algorithmic fairness has been extensively studied in graph-based applications. In contrast to algorithmic fairness on independent and identically distributed (i.i.d.) data, fairness in graph mining has exclusive backgrounds, taxonomies, and fulfilling techniques. In this survey, we provide a comprehensive and up-to-date introduction of existing literature under the context of fair graph mining. Specifically, we propose a novel taxonomy of fairness notions on graphs, which sheds light on their connections and differences. We further present an organized summary of existing techniques that promote fairness in graph mining. Finally, we discuss current research challenges and open questions, aiming at encouraging cross-breeding ideas and further advances. Graph-structured data is pervasive in diverse real-world Compared with achieving fairness in the context of independent applications, e.g., E-commerce [102], [121], health care [37], and identically distributed (i.i.d.) data, fulfilling [53], traffic forecasting [72], [100], and drug discovery [15], fairness in graph mining can be non-trivial due to two [172]. The first challenge is to formulate proper have been proposed to gain a deeper understanding of such fairness notions as the criteria to determine the existence of data. These algorithms have shown promising performance unfairness (i.e., bias). Although a vast amount of traditional on graph analytical tasks such as node classification [59], algorithmic fairness notions have been proposed centered [86], [161] and link prediction [4], [103], [109], contributing on i.i.d. For example, the same population can be most of them lack fairness considerations. Consequently, connected with different topologies as in Figure 1a and 1b, they could yield discriminatory results towards certain populations where each node represents an individual, and the color when such algorithms are exploited in humancentered of nodes denotes their demographic subgroup membership, applications [80]. Compared with the graph topology job recommender system may unfavorably recommend in Figure 1a, the topology in Figure 1b has more intra-group fewer job opportunities to individuals of a certain edges than inter-group edges. The dominance of intra-group gender [97] or individuals in an underrepresented ethnic edges in the graph topology is a common type of bias group [150].

Building a recommendation system involves analyzing user data, which can potentially leak sensitive information about users. Anonymizing user data is often not sufficient for preserving user privacy. Motivated by this, we propose a privacy-preserving recommendation system based on the differential privacy framework and matrix factorization, which is one of the most popular algorithms for recommendation systems. As differential privacy is a powerful and robust mathematical framework for designing privacy-preserving machine learning algorithms, it is possible to prevent adversaries from extracting sensitive user information even if the adversary possesses their publicly available (auxiliary) information. We implement differential privacy via the Gaussian mechanism in the form of output perturbation and release user profiles that satisfy privacy definitions. We employ R\'enyi Differential Privacy for a tight characterization of the overall privacy loss. We perform extensive experiments on real data to demonstrate that our proposed algorithm can offer excellent utility for some parameter choices, while guaranteeing strict privacy.

Sequential recommendation models, models that learn from chronological user-item interactions, outperform traditional recommendation models in many settings. Despite the success of sequential recommendation models, their robustness has recently come into question. Two properties unique to the nature of sequential recommendation models may impair their robustness - the cascade effects induced during training and the model's tendency to rely too heavily on temporal information. To address these vulnerabilities, we propose Cascade-guided Adversarial training, a new adversarial training procedure that is specifically designed for sequential recommendation models. Our approach harnesses the intrinsic cascade effects present in sequential modeling to produce strategic adversarial perturbations to item embeddings during training. Experiments on training state-of-the-art sequential models on four public datasets from different domains show that our training approach produces superior model ranking accuracy and superior model robustness to real item replacement perturbations when compared to both standard model training and generic adversarial training.

State-of-the-art methods on conversational recommender systems (CRS) leverage external knowledge to enhance both items' and contextual words' representations to achieve high quality recommendations and responses generation. However, the representations of the items and words are usually modeled in two separated semantic spaces, which leads to misalignment issue between them. Consequently, this will cause the CRS to only achieve a sub-optimal ranking performance, especially when there is a lack of sufficient information from the user's input. To address limitations of previous works, we propose a new CRS framework KLEVER, which jointly models items and their associated contextual words in the same semantic space. Particularly, we construct an item descriptive graph from the rich items' textual features, such as item description and categories. Based on the constructed descriptive graph, KLEVER jointly learns the embeddings of the words and items, towards enhancing both recommender and dialog generation modules. Extensive experiments on benchmarking CRS dataset demonstrate that KLEVER achieves superior performance, especially when the information from the users' responses is lacking.

Graph Neural Networks (GNNs) have been widely applied on a variety of real-world applications, such as social recommendation. However, existing GNN-based models on social recommendation suffer from serious problems of generalization and oversmoothness, because of the underexplored negative sampling method and the direct implanting of the off-the-shelf GNN models. In this paper, we propose a succinct multi-network GNN-based neural model (NeMo) for social recommendation. Compared with the existing methods, the proposed model explores a generative negative sampling strategy, and leverages both the positive and negative user-item interactions for users' interest propagation. The experiments show that NeMo outperforms the state-of-the-art baselines on various real-world benchmark datasets (e.g., by up to 38.8% in terms of NDCG@15).

It might have been the tiny middle-aged man I matched with on Hinge who tried to lure me into his very short arms by telling me a well-rehearsed, technically touching story about the cancer charity he set up for his dead wife. Or it may have been the (indefinitely benched) Premier League player who picked me up in a leased Maserati which no part of my skin was allowed to touch. Or perhaps it was the guy who brought his laminated CV to a Brixton cocktail bar and tapped his finger on the Oxford University entry for an hour (I had, prematurely, ordered chicken wings I felt unable to abandon). Quite possibly, it was all of them and others combined. But in any case, after years of calamitous dates with random strangers that sounded fun enough but face to face made me want to remove my insides and wash them, I snapped and vowed to never search the web for love again.