Efficient Incremental Cooccurrence Analysis for Item-Based Collaborative Filtering

As a non-linear data structure consisting of nodes and edges, the graph data span many different domains. In the real world, applications based on such data structures are always time-sensitive, that is, the value of graph data tends to decrease with time. Furthermore, the application based on spatio-temporal graph is one of the typical representatives of time-sensitive, since the time dimension is an inherent feature of spatio-temporal data. The Distributed Stream Processing Engine (DSPE) seems an excellent choice for the above requirement, which is commonly partitioned and concurrently processed by a number of threads to maximize the throughput. However, it is not feasible to do such mission directly using the traditional DSPE. In this paper, we propose a computational model suitable for handling the spatio-temporal graph in DSPE, by reconstructing the DSPE’s parallel processing slots. Specifically, our proposal includes a general processing framework to deal with the data structure of the spatio-temporal graph, a state information compensation mechanism to ensure the correctness of processing such stateful operation in DSPE, a lightweight summary information calculation method to ensure the performance of the system. Empirical studies on real-world stream applications validate the usefulness of our proposals and prove the considerable advantage of our approaches over state-of-the-art solutions in the literature.

Recommender Systems (RS) influence everyday decisions, yet most remain optimized for short-term engagement or commercial gain. RS4SD aims to shift this focus by exploring how RS can contribute to sustainable development through behavioral change and nudging strategies. Aligned with the UN Sustainable Development Goals (SDG), RS4SD will highlight applications that promote responsible consumption, sustainable mobility, healthy eating, and digital well-being. In particular, we will focus on how AI and RS can be designed to foster sustainable behaviors through multi-objective optimization and ethically aligned interventions. These objectives are directly tied to the UN SDG, and we welcome all contributions showcasing RS in support of these goals. A central theme of the workshop is the integration of behavioral science and AI to design interventions that guide users toward more sustainable and healthier choices while preserving individual autonomy. Topics of interest include multi-objective recommendation, health-aware RS, eco-friendly product and tourism RS, as well as novel evaluation metrics that go beyond accuracy to capture societal impact. RS4SD will bring together researchers, stakeholders and practitioners from RS, AI, sustainability, and behavioral science to share models, datasets, frameworks, and real-world use cases. The workshop encourages interdisciplinary collaboration and aims to build a community dedicated to responsible, behavior-aware RS that benefit both individuals and society.

Real world use of sutimlimab in patients with cold agglutinin disease: An international study

The proliferation of real-time artificial intelligence (AI) and machine learning (ML) systems has amplified the demand for robust, low-latency state management techniques capable of operating at scale. From streaming feature extraction to online model inference and complex event processing, stateful operations lie at the core of intelligent data-driven pipelines. However, managing this state in distributed environments presents numerous challenges, including fault tolerance, efficient recovery, incremental updates, and tight latency budgets. This paper explores RocksDB, a high-performance, embeddable key-value store based on a log-structured merge-tree (LSM) architecture, as a state backend solution for real-time applications. We delve into the internal mechanisms that make RocksDB particularly well-suited for low-latency, high-throughput workloads, such as background compaction, memory/disk tiering, and custom serialization strategies. The article details practical integration techniques with distributed stream processing engines such as Apache Flink and Kafka Streams, emphasizing checkpointing, state TTL, and asynchronous snapshotting. We also introduce a set of design patterns for real-time AI/ML applications — including online feature stores, real-time recommender systems, and stateful anomaly detection — and show how RocksDB enables efficient, fault-tolerant management of evolving application state. Through empirical evaluations, we benchmark performance trade-offs between RocksDB and alternative backends (e.g., in-memory, Redis, Cassandra), and present optimizations that significantly improve state access latency, recovery time, and disk footprint. By providing a comprehensive review of RocksDB’s role in real-time state management, this work serves as both a scholarly reference and a practical guide for engineers, researchers, and system architects building the next generation of AI/ML-driven streaming systems.

Recommender systems are typically biased toward a small group of users, leading to severe unfairness in recommendation performance, i.e., User-Oriented Fairness (UOF) issue. Existing research on UOF exhibits notable limitations in two phases of recommendation models. In the training phase, current methods fail to tackle the root cause of the UOF issue, which lies in the unfair training process between advantaged and disadvantaged users. In the evaluation phase, the current UOF metric lacks the ability to comprehensively evaluate varying cases of unfairness. In this paper, we aim to address the aforementioned limitations and ensure recommendation models treat user groups of varying activity levels equally. In the training phase, we propose a novel Intra- and Inter-GrOup Optimal Transport framework (II-GOOT) to alleviate the data sparsity problem for disadvantaged users and narrow the training gap between advantaged and disadvantaged users. In the evaluation phase, we introduce a novel metric called ?-UOF, which enables the identification and assessment of various cases of UOF. This helps prevent recommendation models from leading to unfavorable fairness outcomes, where both advantaged and disadvantaged users experience subpar recommendation performance. We conduct extensive experiments on three real-world datasets based on four backbone recommendation models to prove the effectiveness of ?-UOF and the efficiency of our proposed II-GOOT.

295 - Real world use of treatments in interstitial cystitis/painful bladder syndrome: Outcome of an online survey

The paper describes a field evaluation of the automated ‘reverse directory assistance’ service presently in use in Italy in which information about names and addresses is provided by a TTS system. A simulation of the service using a natural voice was also run to get comparative data. Both services were accessed from an office room and a call-box on the street. Different evaluation metrics, such as intelligibility, task completion, task correctness, transaction success, and user's reactions were used. The aim of the work was to evaluate TTS synthesis in real world use and to make a comparison between laboratory data and data on system performance in a real application. Such a comparison suggested that in laboratory tests more attention should be dedicated to simulate more closely the conditions that can be predicted in real world use, by including important aspects that are generally not taken into consideration in laboratory tests and that are likely to have a large influence on TTS system performance such as environmental noise, prosody, and task complexity. The results also underline the importance of field evaluations to get an overall view of the usability of a service in real applications and with users who are as similar as possible to actual users.

OncotypeDx testing is now routinely used to help decide management of hormone positive HER2 negative breast cancer. We have reviewed adjuvant treatment and long-term outcomes of breast cancer patients in those who had a genomic OncotypeDx study performed by the oncology team based at the Northern Centre for Cancer Care (NCCC) in Newcastle Upon Tyne over a 10 year period between 2011-2021. Guidance on the use of chemotherapy according to age and recurrence score changed from July 2018, which has been factored in to our review. We also reviewed the other clinicopathological features that could affect outcomes, including tumour size, grade, nodal status , Nottingham Prognostic index and the presence or absence of in situ disease and lymphovascular invasion. The notes of 908 patients who underwent a total of 974 oncotype Dx scores were reviewed to assess:1.Were the management decisions in line with the guidance on recurrence scores in use at that time?2.What were the outcomes for these patients (we have assessed disease free and overall survival for those who have completed 3 years or more of follow up)?3.For patients who relapsed, would a different decision have been made if current guidelines are applied?. 508 tumours had a low recurrence score (18 or less) and would typically be advised that chemotherapy would not be of benefit. 198 tumours scored in the intermediate group and a decision about chemotherapy currently would be made on the basis of their age. 268 tumours had a high recurrence score of 25 or greater and current advice would advocate chemotherapy in this group. The cut off figures for oncotype score groups have changed with previous ‘intermediate’ recurrence score figures from 18-30, and the ‘high’ score category above 30. 232 tumours of the 974 were node positive (80 with micrometastases, 148 with 1-3 nodes, and 4 had more than 4 involved nodes). In the 255 records evaluated thus far for patient outcome, only 22 relapses have occurred, with 9 local recurrences and 13 distant recurrences. Only two patients in the low recurrence score group evaluated so far (n=147) received chemotherapy and there were 6 patients with recurrences in this group; 4 were local and 3 distant. In the high recurrence score group (n=99 )85 patients received chemotherapy and 14 patients did not, of whom 5 were due to patient choice. Seven patients have so far relapsed (2 local & 5 distant recurrences). In the intermediate group 15 patients received chemotherapy of the total group evaluated to date(n=73). Six patients in the intermediate group have relapsed (2 local & 4 distant recurrences). Under modern guidelines, only two further patients in this group would have been offered chemotherapy. 25 of the patients in the intermediate group were 55 years or above and 4 of these received chemotherapy - under current UK guidance these patients would avoid chemotherapy. Whilst the aim is to share results from the complete dataset in our poster, early results from this study confirm the benefit of OncotypeDx testing in the real world management of patients with breast cancer. AcknowledgementsMark Verrill, NicCresti, Daniella Lee, Radha Todd, Helen Turnbull, Kathryn Wright, NajibahMahtab, Ed Hallam, Sarah Reynia Citation Format: Abigail Gault, Jayshree Veeratterapillay, Wendy Taylor. Real world use of OncotypeDx testing in the management of breast cancer. The North East England experience [abstract]. In: Proceedings of the 2021 San Antonio Breast Cancer Symposium; 2021 Dec 7-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2022;82(4 Suppl):Abstract nr P1-08-28.

Real world outcomes in patients with acquired thrombotic thrombocytopenic purpura (TTP) treated with caplacizumab

Nicotine levels, withdrawal symptoms, and smoking reduction success in real world use: A comparison of cigarette smokers and dual users of both cigarettes and E-cigarettes

BackgroundIndividuals with diabetes are using social media as a method to share and gather information about their health via the diabetes online community. Infoveillance is one methodological approach to examine health care trends. However, infoveillance, while very effective in identifying many real-world health trends, may miss opportunities that use photographs as primary sources for data. We propose a new methodology, photosurveillance, in which photographs are analyzed to examine real-world trends.ObjectiveThe purpose of this research is to (1) assess the use of photosurveillance as a research method to examine real-world trends in diabetes and (2) report on real-world use of continuous glucose monitoring (CGM) on Instagram.MethodsThis exploratory mixed methods study examined all photographs posted on Instagram that were identified with the hashtag #dexcom over a 3-month period—December 2016 to February 2017. Photographs were coded by CGM location on the body. Original posts and corresponding comments were textually coded for length of CGM device wear and CGM failure and were analyzed for emerging themes.ResultsA total of 2923 photographs were manually screened; 12.08% (353/2923) depicted a photograph with a CGM site location. The majority (225/353, 63.7%) of the photographs showed a CGM site in an off-label location, while 26.2% (92/353) were in an FDA-approved location (ie, abdomen) and 10.2% (36/353) were in an unidentifiable location. There were no significant differences in the number of likes or comments based on US Food and Drug Administration (FDA) approval. Five themes emerged from the analysis of original posts (N=353) and corresponding comments (N=2364): (1) endorsement of CGM as providing a sense of well-being; (2) reciprocating information, encouragement, and support; (3) reciprocating CGM-related frustrations; (4) life hacks to optimize CGM use; and (5) sharing and learning about off-label CGM activity.ConclusionsOur results indicate that individuals successfully used CGM in off-label locations, posting photos of these areas with greater frequency than of the abdomen, with no indication of sensor failure. While these photographs only capture a snapshot in time, these posts can be used to inform providers and industry leaders of real-world trends in CGM use. Additionally, there were instances in which sensors were worn beyond the FDA-approved 7-day period; however, they represented the minority in this study.

Cyber-physical systems (CPS) are often characterized as smart systems, which intelligently interact with other systems across information and physical interfaces. Cyber-physical systems (CPS) are fitting into modern society. CPS integrate multiple techniques, including distributed computing, communication and automatic control, to support variety of intelligent services and applications in many fields, such as transportation, healthcare, entertainment and city infrastructure. Recommender systems in CPS, which always provide information recommendations for users based on historical ratings collected from a single domain only, suffer from the data sparsity problem. Recently, several recommendation models have been proposed to transfer knowledge across multiple domains to alleviate the sparsity problem, which typically assumes that multiple domains share a latent common rating pattern. Recommender systems always results into faster and efficient options/choices as per user’s demands. This technology helps us in retrieval and access of different services like in Healthcare sector, Education, E-Commerce, etc. During the last few decades, with the rise of Youtube, Amazon, Netflix and many other such web services, recommender systems have taken more and more place in our lives. From e-commerce (suggest to buyers articles that could interest them) to online advertisement (suggest to users the right contents, matching their preferences), recommender systems are today unavoidable in our daily online journeys. In this paper, a proposed system architecture focusses on IoT applications utilizing recommender systems for offering number of services to users. Also, various Cyber Physical Recommender Systems are proposed to offer standard quality of service (QoS) for various IoT applications.

A Personalized Recommender System from Probabilistic Relational Model and Users’ Preferences

At present, it can be explained that the recommendation system is mostly designed for a specific recommendation model, and its scalability is weak. It is not enough for the emerging recommendation models, such as complex and mixed models with deep neural networks.Knowledge maps as a highly readable external knowledge carrier provide great possibilities for improving the ability of algorithms to interpret.In essence, the knowledge map is intended to describe the various entities or concepts and their relationships that exist in the real world, which constitute a huge semantic network diagram, nodes represent entities or concepts, and edges are composed of attributes or relationships.Based on the current research status, this paper analyzes and studies the concept of knowledge map, the combination of knowledge map and recommendation system, the object of interpretability and the application of knowledge map in interpretability model, combined with relevant recommendation models. The knowledge map, open up the relationship between the media, flexibly choose the most suitable medium according to the specific situation to recommend and explain the user.

Recent studies reveal that recommender systems are vulnerable to data poisoning attack due to their openness nature. In data poisoning attack, the attacker typically recruits a group of controlled users to inject well-crafted user-item interaction data into the recommendation model's training set to modify the model parameters as desired. Thus, existing attack approaches usually require full access to the training data to infer items' characteristics and craft the fake interactions for controlled users. However, such attack approaches may not be feasible in practice due to the attacker's limited data collection capability and the restricted access to the training data, which sometimes are even perturbed by the privacy preserving mechanism of the service providers. Such design-reality gap may cause failure of attacks. In this paper, we fill the gap by proposing two novel adversarial attack approaches to handle the incompleteness and perturbations in user-item interaction data. First, we propose a bi-level optimization framework that incorporates a probabilistic generative model to find the users and items whose interaction data is sufficient and has not been significantly perturbed, and leverage these users and items' data to craft fake user-item interactions. Moreover, we reverse the learning process of recommendation models and develop a simple yet effective approach that can incorporate context-specific heuristic rules to handle data incompleteness and perturbations. Extensive experiments on two datasets against three representative recommendation models show that the proposed approaches can achieve better attack performance than existing approaches.