Search

We consider a ubiquitous scenario in the study of Influence Maximization (IM), in which there is limited knowledge about the topology of the diffusion network. We set the IM problem in a multi-round diffusion campaign, aiming to maximize the number of distinct users that are influenced. Leveraging the capability of bandit algorithms to effectively balance the objectives of exploration and exploitation, as well as the expressivity of neural networks, our study explores the application of neural bandit algorithms to the IM problem. We propose the framework IM-GNB (Influence Maximization with Graph Neural Bandits), where we provide an estimate of the users' probabilities of being influenced by influencers (also known as diffusion seeds). This initial estimate forms the basis for constructing both an exploitation graph and an exploration one. Subsequently, IM-GNB handles the exploration-exploitation tradeoff, by selecting seed nodes in real-time using Graph Convolutional Networks (GCN), in which the pre-estimated graphs are employed to refine the influencers' estimated rewards in each contextual setting. Through extensive experiments on two large real-world datasets, we demonstrate the effectiveness of IM-GNB compared with other baseline methods, significantly improving the spread outcome of such diffusion campaigns, when the underlying network is unknown., Comment: To appear at the 2024 ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD)

RR Lyrae stars are standard candles with characteristic photometric variability and serve as powerful tracers of Galactic structure, substructure, accretion history, and dark matter content. Here we report the discovery of distant RR Lyrae stars, including some of the most distant stars known in the Milky Way halo, with Galactocentric distances of approximately 300 kpc. We use time-series u*g'i'z' Canada-France-Hawaii Telescope/MegaCam photometry from the Next Generation Virgo Cluster Survey (NGVS). We employ a template light curve fitting method based on empirical Sloan Digital Sky Survey (SDSS) Stripe 82 RR Lyrae data to identify RR Lyrae candidates in the NGVS data set. We eliminate several hundred suspected quasars and identify 180 RR Lyrae candidates, with heliocentric distances of approximately 20--300 kpc. The halo stellar density distribution is consistent with an r^(-4.09 +/- 0.10) power-law radial profile over most of this distance range with no signs of a break. The distribution of ab-type RR Lyrae in a period-amplitude plot (Bailey diagram) suggests that the mean metallicity of the halo decreases outwards. Compared to other recent RR Lyrae surveys, like Pan-STARRS1 (PS1), the High Cadence Transient Survey (HiTS), and the Dark Energy Survey (DES), our NGVS study has better single-epoch photometric precision and a comparable number of epochs but smaller sky coverage. At large distances, our RR Lyrae sample appears to be relatively pure and complete, with well-measured periods and amplitudes. These newly discovered distant RR Lyrae stars are important additions to the few secure stellar tracers beyond 150 kpc in the Milky Way halo., Comment: Accepted by ApJ

In this paper, we revisit the problem of influence maximization with fairness, which aims to select k influential nodes to maximise the spread of information in a network, while ensuring that selected sensitive user attributes are fairly affected, i.e., are proportionally similar between the original network and the affected users. Recent studies on this problem focused only on extremely small networks, hence the challenge remains on how to achieve a scalable solution, applicable to networks with millions or billions of nodes. We propose an approach that is based on learning node representations for fair spread from diffusion cascades, instead of the social connectivity s.t. we can deal with very large graphs. We propose two data-driven approaches: (a) fairness-based participant sampling (FPS), and (b) fairness as context (FAC). Spread related user features, such as the probability of diffusing information to others, are derived from the historical information cascades, using a deep neural network. The extracted features are then used in selecting influencers that maximize the influence spread, while being also fair with respect to the chosen sensitive attributes. In FPS, fairness and cascade length information are considered independently in the decision-making process, while FAC considers these information facets jointly and considers correlations between them. The proposed algorithms are generic and represent the first policy-driven solutions that can be applied to arbitrary sets of sensitive attributes at scale. We evaluate the performance of our solutions on a real-world public dataset (Sina Weibo) and on a hybrid real-synthethic dataset (Digg), which exhibit all the facets that we exploit, namely diffusion network, diffusion traces, and user profiles. These experiments show that our methods outperform the state-the-art solutions in terms of spread, fairness, and scalability.

News recommendation is one of the most challenging tasks in recommender systems, mainly due to the ephemeral relevance of news to users. As social media, and particularly microblogging applications like Twitter or Weibo, gains popularity as platforms for news dissemination, personalized news recommendation in this context becomes a significant challenge. We revisit news recommendation in the microblogging scenario, by taking into consideration social interactions and observations tracing how the information that is up for recommendation spreads in an underlying network. We propose a deep-learning based approach that is diffusion and influence-aware, called Influence-Graph News Recommender (IGNiteR). It is a content-based deep recommendation model that jointly exploits all the data facets that may impact adoption decisions, namely semantics, diffusion-related features pertaining to local and global influence among users, temporal attractiveness, and timeliness, as well as dynamic user preferences. To represent the news, a multi-level attention-based encoder is used to reveal the different interests of users. This news encoder relies on a CNN for the news content and on an attentive LSTM for the diffusion traces. For the latter, by exploiting previously observed news diffusions (cascades) in the microblogging medium, users are mapped to a latent space that captures potential influence on others or susceptibility of being influenced for news adoptions. Similarly, a time-sensitive user encoder enables us to capture the dynamic preferences of users with an attention-based bidirectional LSTM. We perform extensive experiments on two real-world datasets, showing that IGNiteR outperforms the state-of-the-art deep-learning based news recommendation methods., Comment: News recommendation, deep learning, diffusion

W Ursa Majoris (W UMa)-type contact binary systems (CBs) are useful statistical distance indicators because of their large numbers. Here, we establish (orbital) period-luminosity relations (PLRs) in 12 optical-to-mid-infrared bands (GBV RIJHKsW1W2W3W4) based on 183 nearby W UMa-type CBs with accurate Tycho-Gaia parallaxes. The 1{\sigma} dispersion of the PLRs decreases from optical to near- and mid-infrared wavelengths. The minimum scatter, 0.16 mag, implies that W UMa-type CBs can be used to recover distances to 7% precision. Applying our newly determined PLRs to 19 open clusters containing W UMa-type CBs demonstrates that the PLR and open cluster CB distance scales are mutually consistent to within 1%. Adopting our PLRs as secondary distance indicators, we compiled a catalog of 55,603 CBs candidates, of which 80% have distance estimates based on a combination of optical, near-, and mid-infrared photometry. Using Fourier decomposition, 27,318 high-probability W UMa-type CBs were selected. The resulting 8% distance accuracy implies that our sam- ple encompasses the largest number of objects with accurate distances within a local volume with a radius of 3 kpc available to date. The distribution of W UMa-type CBs in the Galaxy suggests that in different environments, the CB luminosity function may be different: larger numbers of brighter (longer-period) W UMa-type CBs are found in younger environments., Comment: 26 pages, 6 figures, accepted by The Astrophysical Journal