Music streaming services heavily rely on their recommendation engines to continuously provide content to their consumers. Sequential recommendation consequently has seen considerable attention in current literature, where state of the art approaches focus on self-attentive models leveraging contextual information such as long and short-term user history and item features; however, most of these studies focus on long-form content domains (retail, movie, etc.) rather than short-form, such as music. Additionally, many do not explore incorporating negative session-level feedback during training. In this study, we investigate the use of transformer-based self-attentive architectures to learn implicit session-level information for sequential music recommendation. We additionally propose a contrastive learning task to incorporate negative feedback (e.g skipped tracks) to promote positive hits and penalize negative hits. This task is formulated as a simple loss term that can be incorporated into a variety of deep learning architectures for sequential recommendation. Our experiments show that this results in consistent performance gains over the baseline architectures ignoring negative user feedback.

Computational modeling of artwork meaning is complex and difficult. This is because art interpretation is multidimensional and highly subjective. This paper experimentally investigated the degree to which a state-of-the-art Deep Convolutional Neural Network (DCNN), a popular Machine Learning approach, can correctly distinguish modern conceptual art work into the galleries devised by art curators. Two hypotheses were proposed to state that the DCNN model uses Exhibited Properties for classification, like shape and color, but not Non-Exhibited Properties, such as historical context and artist intention. The two hypotheses were experimentally validated using a methodology designed for this purpose. VGG-11 DCNN pre-trained on ImageNet dataset and discriminatively fine-tuned was trained on handcrafted datasets designed from real-world conceptual photography galleries. Experimental results supported the two hypotheses showing that the DCNN model ignores Non-Exhibited Properties and uses only Exhibited Properties for artwork classification. This work points to current DCNN limitations, which should be addressed by future DNN models.

Ed Newton-Rex says generative AI has an ethics problem. He ought to know, because he used to be part of the fast-growing industry. Newton-Rex was TikTok's head AI designer and then an executive at Stability AI until he quit in disgust in November over the company's stance on collecting training data. After his high-profile departure, Newton-Rex threw himself into conversation after conversation about what building AI ethically would look like in practice. "It struck me that there are a lot of people who want to use generative AI models that treat creators fairly," he says.

If you were listening to rock radio in the early nineteen-nineties, you might have heard a song called "Sober," which reflected the genre's new mood. In the wake of Nirvana's success, rock and roll was growing more sullen and more introverted, embracing dark colors and minor keys. "Sober," which was released in 1993, had a heavy neck-snapping rhythm and a howling, tormented refrain: "Why can't we not be sober? The song was a breakthrough hit for a California band called Tool, which played the Lollapalooza tour the same year, and made a sufficiently impressive racket to be elevated from the second stage to the main stage, joining Alice in Chains and Rage Against the Machine. Back then, bands such as these were often classified as "alternative," a rather vague and cringeworthy term that nevertheless turned out to be a pretty good description of Tool, which has spent the past three decades building an impressive following, and legacy, by stubbornly refusing to act the way rock bands are supposed to.

Samsung unveiled its Galaxy S24 devices at its first Unpacked of the year. As expected, the three smartphones have a heavy focus on artificial intelligence-powered features, from the likes of live translations to image editing. Galaxy AI, as Samsung is calling the devices' overarching AI system, is behind a number of communication-focused functions. For one thing, Galaxy S24 devices will natively support live, two-way translations on phone calls without the need for a third-party app, Samsung says. Since processing for most AI features is handled on-device with the help of the Snapdragon 8 Gen 3 Chipset and its neural processing unit, the conversations will stay private (well, aside from eavesdroppers who might catch one half of the chat).

Stay up to date on the latest AI technology advancements and learn about the challenges and opportunities AI presents now and for the future.

It's one of the most well-known companies in the world, and now Apple has officially been crowned the world's biggest phonemaker. While Samsung has taken the top spot every year since 2010, it was finally knocked off its pedestal by Apple in 2023. Figures released by the International Data Corporation (IDC) reveal how Apple took 20.1 per cent of the market share last year – a 3.7 per cent increase on 2022. 'The biggest winner is clearly Apple,' said Nabila Popal, research director with IDC's Worldwide Tracker team. 'Not only is Apple the only player in the Top 3 to show positive growth annually, but also bags the number 1 spot annually for the first time ever.'

Reinforcement learning (RL) has gained traction for enhancing user long-term experiences in recommender systems by effectively exploring users' interests. However, modern recommender systems exhibit distinct user behavioral patterns among tens of millions of items, which increases the difficulty of exploration. For example, user behaviors with different activity levels require varying intensity of exploration, while previous studies often overlook this aspect and apply a uniform exploration strategy to all users, which ultimately hurts user experiences in the long run. To address these challenges, we propose User-Oriented Exploration Policy (UOEP), a novel approach facilitating fine-grained exploration among user groups. We first construct a distributional critic which allows policy optimization under varying quantile levels of cumulative reward feedbacks from users, representing user groups with varying activity levels. Guided by this critic, we devise a population of distinct actors aimed at effective and fine-grained exploration within its respective user group. To simultaneously enhance diversity and stability during the exploration process, we further introduce a population-level diversity regularization term and a supervision module. Experimental results on public recommendation datasets demonstrate that our approach outperforms all other baselines in terms of long-term performance, validating its user-oriented exploration effectiveness. Meanwhile, further analyses reveal our approach's benefits of improved performance for low-activity users as well as increased fairness among users.

In the era of information proliferation, discerning the credibility of news content poses an ever-growing challenge. This paper introduces RELIANCE, a pioneering ensemble learning system designed for robust information and fake news credibility evaluation. Comprising five diverse base models, including Support Vector Machine (SVM), naive Bayes, logistic regression, random forest, and Bidirectional Long Short Term Memory Networks (BiLSTMs), RELIANCE employs an innovative approach to integrate their strengths, harnessing the collective intelligence of the ensemble for enhanced accuracy. Experiments demonstrate the superiority of RELIANCE over individual models, indicating its efficacy in distinguishing between credible and non-credible information sources. RELIANCE, also surpasses baseline models in information and news credibility assessment, establishing itself as an effective solution for evaluating the reliability of information sources.

In the age of the infodemic, it is crucial to have tools for effectively monitoring the spread of rampant rumors that can quickly go viral, as well as identifying vulnerable users who may be more susceptible to spreading such misinformation. This proactive approach allows for timely preventive measures to be taken, mitigating the negative impact of false information on society. We propose a novel approach to predict viral rumors and vulnerable users using a unified graph neural network model. We pre-train network-based user embeddings and leverage a cross-attention mechanism between users and posts, together with a community-enhanced vulnerability propagation (CVP) method to improve user and propagation graph representations. Furthermore, we employ two multi-task training strategies to mitigate negative transfer effects among tasks in different settings, enhancing the overall performance of our approach. We also construct two datasets with ground-truth annotations on information virality and user vulnerability in rumor and non-rumor events, which are automatically derived from existing rumor detection datasets. Extensive evaluation results of our joint learning model confirm its superiority over strong baselines in all three tasks: rumor detection, virality prediction, and user vulnerability scoring. For instance, compared to the best baselines based on the Weibo dataset, our model makes 3.8\% and 3.0\% improvements on Accuracy and MacF1 for rumor detection, and reduces mean squared error (MSE) by 23.9\% and 16.5\% for virality prediction and user vulnerability scoring, respectively. Our findings suggest that our approach effectively captures the correlation between rumor virality and user vulnerability, leveraging this information to improve prediction performance and provide a valuable tool for infodemic surveillance.