The task of reconstructing a matrix given a sample of observed entries is known as the \emph{matrix completion problem}. Such a consideration arises in a wide variety of problems, including recommender systems, collaborative filtering, dimensionality reduction, image processing, quantum physics or multi-class classification to name a few. Most works have focused on recovering an unknown real-valued low-rank matrix from randomly sub-sampling its entries. Here, we investigate the case where the observations take a finite numbers of values, corresponding for examples to ratings in recommender systems or labels in multi-class classification. We also consider a general sampling scheme (non-necessarily uniform) over the matrix entries. The performance of a nuclear-norm penalized estimator is analyzed theoretically. More precisely, we derive bounds for the Kullback-Leibler divergence between the true and estimated distributions. In practice, we have also proposed an efficient algorithm based on lifted coordinate gradient descent in order to tackle potentially high dimensional settings.

Accurately measuring portfolio similarity is critical for a wide range of financial applications, including Exchange-traded Fund (ETF) recommendation, portfolio trading, and risk alignment. Existing similarity measures often rely on exact asset overlap or static distance metrics, which fail to capture similarities among the constituents (e.g., securities within the portfolio) as well as nuanced relationships between partially overlapping portfolios with heterogeneous weights. We introduce STRAPSim (Semantic, Two-level, Residual-Aware Portfolio Similarity), a novel method that computes portfolio similarity by matching constituents based on semantic similarity, weighting them according to their portfolio share, and aggregating results via residual-aware greedy alignment. We benchmark our approach against Jaccard, weighted Jaccard, as well as BERTScore-inspired variants across public classification, regression, and recommendation tasks, as well as on corporate bond ETF datasets. Empirical results show that our method consistently outperforms baselines in predictive accuracy and ranking alignment, achieving the highest Spearman correlation with return-based similarity. By leveraging constituent-aware matching and dynamic reweighting, portfolio similarity offers a scalable, interpretable framework for comparing structured asset baskets, demonstrating its utility in ETF benchmarking, portfolio construction, and systematic execution.

AI-based recommender systems increasingly influence recruitment decisions. Thus, transparency and responsible adoption in Human Resource Management (HRM) are critical. This study examines how HR managers' AI literacy influences their subjective perception and objective understanding of explainable AI (XAI) elements in recruiting recommender dashboards. In an online experiment, 410 German-based HR managers compared baseline dashboards to versions enriched with three XAI styles: important features, counterfactuals, and model criteria. Our results show that the dashboards used in practice do not explain AI results and even keep AI elements opaque. However, while adding XAI features improves subjective perceptions of helpfulness and trust among users with moderate or high AI literacy, it does not increase their objective understanding. It may even reduce accurate understanding, especially with complex explanations. Only overlays of important features significantly aided the interpretations of high-literacy users. Our findings highlight that the benefits of XAI in recruitment depend on users' AI literacy, emphasizing the need for tailored explanation strategies and targeted literacy training in HRM to ensure fair, transparent, and effective adoption of AI.

Personalized text generation has become crucial for adapting language models to diverse and evolving users' personal context across cultural, temporal, and contextual dimensions. While existing methods often rely on centralized fine-tuning or static preference alignment, they struggle to achieve real-time adaptation under resource constraints inherent to personal devices. This limitation creates a dilemma: large cloud-based models lack access to localized user-specific information, while small on-device models cannot match the generation quality of their cloud counterparts. To address this dichotomy, we present CoSteer, a novel collaborative framework that enables decoding-time personalization through localized delta steering. Our key insight lies in leveraging the logits difference between personal context-aware and -agnostic outputs from local small models as steering signals for cloud-based LLMs. Specifically, we formulate token-level optimization as an online learning problem, where local delta vectors dynamically adjust the remote LLM's logits within the on-device environment. This approach preserves privacy by transmitting only the final steered tokens rather than raw data or intermediate vectors, while maintaining cloud-based LLMs' general capabilities without fine-tuning. Through comprehensive experiments on various personalized generation tasks, we demonstrate that CoSteer effectively assists LLMs in generating personalized content by leveraging locally stored user profiles and histories, ensuring privacy preservation through on-device data processing while maintaining acceptable computational overhead.

A prominent issue in aligning language models (LMs) to personalized preferences is underspecification -- the lack of information from users about their preferences. A popular trend of injecting such specification is adding a prefix (e.g. prior relevant conversations) to the current user's conversation to steer preference distribution. Most methods passively model personal preferences with prior example preferences pairs. We ask whether models benefit from actively inferring preference descriptions, and address this question by creating a synthetic personalized alignment dataset based on famous people with known public preferences. We then test how effective finetuned 1-8B size models are at inferring and aligning to personal preferences. Results show that higher-quality active prefixes lead to better generalization, more contextually faithful models, and less systematic biases across different protected attributes. All our results suggest active alignment can lead to a more controllable and efficient path for personalized alignment.

Generative recommendation, which directly generates item identifiers, has emerged as a promising paradigm for recommendation systems. However, its potential is fundamentally constrained by the reliance on purely autoregressive training. This approach focuses solely on predicting the next item while ignoring the rich internal structure of a user's interaction history, thus failing to grasp the underlying intent. To address this limitation, we propose Masked History Learning (MHL), a novel training framework that shifts the objective from simple next-step prediction to deep comprehension of history. MHL augments the standard autoregressive objective with an auxiliary task of reconstructing masked historical items, compelling the model to understand ``why'' an item path is formed from the user's past behaviors, rather than just ``what'' item comes next. We introduce two key contributions to enhance this framework: (1) an entropy-guided masking policy that intelligently targets the most informative historical items for reconstruction, and (2) a curriculum learning scheduler that progressively transitions from history reconstruction to future prediction. Experiments on three public datasets show that our method significantly outperforms state-of-the-art generative models, highlighting that a comprehensive understanding of the past is crucial for accurately predicting a user's future path. The code will be released to the public.

Artificial intelligence technology plays a crucial role in recommending prescriptions for traditional Chinese medicine (TCM). Previous studies have made significant progress by focusing on the symptom-herb relationship in prescriptions. However, several limitations hinder model performance: (i) Insufficient attention to patient-personalized information such as age, BMI, and medical history, which hampers accurate identification of syndrome and reduces efficacy. (ii) The typical long-tailed distribution of herb data introduces training biases and affects generalization ability. (iii) The oversight of the 'monarch, minister, assistant and envoy' compatibility among herbs increases the risk of toxicity or side effects, opposing the 'treatment based on syndrome differentiation' principle in clinical TCM. Therefore, we propose a novel hierarchical structure-enhanced personalized recommendation model for TCM formulas based on knowledge graph diffusion guidance, namely TCM-HEDPR. Specifically, we pre-train symptom representations using patient-personalized prompt sequences and apply prompt-oriented contrastive learning for data augmentation. Furthermore, we employ a KG-guided homogeneous graph diffusion method integrated with a self-attention mechanism to globally capture the non-linear symptom-herb relationship. Lastly, we design a heterogeneous graph hierarchical network to integrate herbal dispensing relationships with implicit syndromes, guiding the prescription generation process at a fine-grained level and mitigating the long-tailed herb data distribution problem. Extensive experiments on two public datasets and one clinical dataset demonstrate the effectiveness of TCM-HEDPR. In addition, we incorporate insights from modern medicine and network pharmacology to evaluate the recommended prescriptions comprehensively. It can provide a new paradigm for the recommendation of modern TCM.

Abstract--With the emergence of Web 2.0 and microservices architecture, the number of Web APIs has increased dramatically, further intensifying the demand for efficient Web API recommendation. Existing solutions typically fall into two categories: recommendation-type methods, which treat each API as a label for classification, and match-type methods, which focus on matching mashups through API retrieval. However, three critical challenges persist: 1) the semantic ambiguities in comparing API and mashup descriptions, 2) the lack of detailed comparisons between the individual API and the mashup in recommendation-type methods, and 3) time inefficiencies for API retrieval in match-type methods. T o address these challenges, we propose W ARBERT, a hierarchical BERT -based model for Web API recommendation. W ARBERT leverages dual-component feature fusion and attention comparison to extract precise semantic representations of API and mashup descriptions. W ARBERT consists of two main components: W ARBERT(R) for Recommendation and W ARBERT(M) for Matching. Specifically, W AR-BERT(R) serves as an initial filter, narrowing down the candidate APIs, while W ARBERT(M) refines the matching process by calculating the similarity between candidate APIs and mashup. The final likelihood of a mashup being matched with an API is determined by combining the predictions from W ARBERT(R) and W ARBERT(M). Additionally, W ARBERT(R) incorporates an auxiliary task of mashup category judgment, which enhances its effectiveness in candidate selection. Experimental results on the ProgrammableWeb dataset demonstrate that W ARBERT outperforms most existing solutions and achieves improvements of up to 11.7% compared to the model MTFM (Multi-T ask Fusion Model), delivering significant enhancements in accuracy and efficiency. ITH the emergence of Web 2.0 and microservice architecture, the number of APIs has increased dramatically [1]. Since 2022, there have been more than 24,000 APIs in ProgrammableWeb [2]. The benefits of Web APIs have led to the emergence of a novel method for developing applications, known as Mashup [3]. Mashup enables developers to integrate existing Web API resources to meet complex requirements without starting from scratch [4], [5].

Ensuring fair outcomes for multiple stakeholders in recommender systems has been studied mostly in terms of algorithmic interventions: building new models with better fairness properties, or using reranking to improve outcomes from an existing algorithm. What has rarely been studied is structural changes in the recommendation ecosystem itself. Our work explores the fairness impact of algorithmic pluralism, the idea that the recommendation algorithm is decoupled from the platform through which users access content, enabling user choice in algorithms. Prior work using a simulation approach has shown that niche consumers and (especially) niche providers benefit from algorithmic choice. In this paper, we use simulation to explore the question of profile portability, to understand how different policies regarding the handling of user profiles interact with fairness outcomes for consumers and providers.

The purpose of this paper is to explore a multi-modal approach to enhancing live broadcast engagement by developing a short video recommendation system that incorporates Multi-modal Graph Convolutional Networks (MMGCN) with user preferences. To provide personalized recommendations tailored to individual interests, the proposed system considers user interaction data, video content features, and contextual information. With the aid of a hybrid approach combining collaborative filtering and content-based filtering techniques, the system can capture nuanced relationships between users, video attributes, and engagement patterns. Three datasets are used to evaluate the effectiveness of the system: Kwai, TikTok, and MovieLens. Compared to baseline models, such as DeepFM, Wide & Deep, LightGBM, and XGBoost, the proposed MMGCN-based model shows superior performance. A notable feature of the proposed model is that it outperforms all baseline methods in capturing diverse user preferences and making accurate, personalized recommendations, resulting in a Kwai F1 score of 0.574, a Tiktok F1 score of 0.506, and a MovieLens F1 score of 0.197. We emphasize the importance of multi-modal integration and user-centric approaches in advancing recommender systems, emphasizing the role they play in enhancing content discovery and audience interaction on live broadcast platforms.