Creator Incentives in Recommender Systems: A Cooperative Game-Theoretic Approach for Stable and Fair Collaboration in Multi-Agent Bandits

arXiv (Cornell University) · 2026-04-09

User interactions in online recommendation platforms create interdependencies among content creators: feedback on one creator's content influences the system's learning and, in turn, the exposure of other creators' contents. To analyze incentives in such settings, we model collaboration as a multi-agent stochastic linear bandit problem with a transferable utility (TU) cooperative game formulation, where a coalition's value equals the negative sum of its members' cumulative regrets. We show that, for identical (homogenous) agents with fixed action sets, the induced TU game is convex under mild algorithmic conditions, implying a non-empty core that contains the Shapley value and ensures both stability and fairness. For heterogeneous agents, the game still admits a non-empty core, though convexity and Shapley value core-membership are no longer guaranteed. To address this, we propose a simple regret-based payout rule that satisfies three out of the four Shapley axioms and also lies in the core. Experiments on MovieLens-100k dataset illustrate when the empirical payout aligns with -- and diverges from -- the Shapley fairness across different settings and algorithms.

Creator Incentives in Recommender Systems: A Cooperative Game-Theoretic Approach for Stable and Fair Collaboration in Multi-Agent Bandits

arXiv (Cornell University) · 2026-04-09

User interactions in online recommendation platforms create interdependencies among content creators: feedback on one creator's content influences the system's learning and, in turn, the exposure of other creators' contents. To analyze incentives in such settings, we model collaboration as a multi-agent stochastic linear bandit problem with a transferable utility (TU) cooperative game formulation, where a coalition's value equals the negative sum of its members' cumulative regrets. We show that, for identical (homogenous) agents with fixed action sets, the induced TU game is convex under mild algorithmic conditions, implying a non-empty core that contains the Shapley value and ensures both stability and fairness. For heterogeneous agents, the game still admits a non-empty core, though convexity and Shapley value core-membership are no longer guaranteed. To address this, we propose a simple regret-based payout rule that satisfies three out of the four Shapley axioms and also lies in the core. Experiments on MovieLens-100k dataset illustrate when the empirical payout aligns with -- and diverges from -- the Shapley fairness across different settings and algorithms.

FieldFormer: Locality-Aware Transformers for Spatio-Temporal Modeling on Sparse Sensor Networks

ArXiv.org · 2025-10-04

Spatio-temporal sensor data in real-world systems is often sparse, noisy, and irregular, making latent field reconstruction fundamentally underconstrained. Under extreme sparsity, multiple physically plausible fields may remain consistent with the same observations, requiring models to rely on inductive biases about locality, transport, and spatial regularity. In such regimes, reliable reconstruction is concentrated around the observational support induced by the sensor network, making sensor-space modeling a more identifiable objective than unconstrained global field recovery. We introduce FieldFormer, a mesh-free transformer architecture for locality-aware sensor-space modeling in persistent sensor networks. For each query, FieldFormer aggregates local evidence using learnable velocity-scaled offsets that adapt neighborhood geometry to spatio-temporal dependencies. Neighborhoods are constructed as fixed maximal sparse contexts over nearby sensors and bounded temporal windows, enabling stable and scalable inference under extreme sparsity. A local transformer encoder integrates neighborhood information, while a coordinate-based neural field formulation supports mesh-free prediction. We evaluate FieldFormer on five synthetic and real-world benchmarks, including anisotropic heat diffusion, shallow-water dynamics, atmospheric transport, and pollution monitoring datasets. Results show that locality-aware reconstruction provides strong advantages when local domains of dependence remain observed, enabling FieldFormer to consistently outperform state-of-the-art baselines on sparse sensor-space prediction tasks.

Generation of a Compendium of Transcription Factor Cascades and Identification of Potential Therapeutic Targets Using Graph Machine Learning

Genes · 2025-11-30

BACKGROUND: Transcription factors (TFs) are critical regulators of gene expression, and their dysregulation is implicated in diseases like cancer. This study aims to create a comprehensive resource of TF cascades to identify potential therapeutic targets. METHODS: We extracted TF interactions from the STRING database, constructed a knowledge graph using graph machine learning, and performed pathway enrichment analysis with Enrichr. Network analysis and PageRank identified influential TFs. RESULTS: We generated 81,488 unique TF cascades, with the longest containing 62 TFs. Key TFs (e.g., MYC, TP53, STAT3) were identified, and enriched pathways included cancer-related processes. A knowledge graph and dataset were made publicly available. CONCLUSIONS: This compendium of TF cascades provides a valuable resource for understanding TF interactions and identifying novel drug targets for precision therapeutics.

MAML: Towards a Faster Web in Developing Regions

ArXiv.org · 2025-01-20

The web experience in developing regions remains subpar, primarily due to the growing complexity of modern webpages and insufficient optimization by content providers. Users in these regions typically rely on low-end devices and limited bandwidth, which results in a poor user experience as they download and parse webpages bloated with excessive third-party CSS and JavaScript (JS). To address these challenges, we introduce the Mobile Application Markup Language (MAML), a flat layout-based web specification language that reduces computational and data transmission demands, while replacing the excessive bloat from JS with a new scripting language centered on essential (and popular) web functionalities. Last but not least, MAML is backward compatible as it can be transpiled to minimal HTML/JavaScript/CSS and thus work with legacy browsers. We benchmark MAML in terms of page load times and sizes, using a translator which can automatically port any webpage to MAML. When compared to the popular Google AMP, across 100 testing webpages, MAML offers webpage speedups by tens of seconds under challenging network conditions thanks to its significant size reductions. Next, we run a competition involving 25 university students porting 50 of the above webpages to MAML using a web-based editor we developed. This experiment verifies that, with little developer effort, MAML is quite effective in maintaining the visual and functional correctness of the originating webpages.

Modeling Economic Viability for Scalable AI Deployment in Emerging Regions

2025-10-01

The costs associated with cloud infrastructure required to power large-scale AI services in emerging regions do not scale proportionally to the challenges hindering the economic viability of compute-intensive services in these regions. Although emerging regions represent vast untapped markets with the potential to provide access to the next billion users, businesses are often forced to endure high customer acquisition costs and initial losses in hopes of long-term profitability. This paper investigates the economics of deploying and operating AI data centers in emerging regions, examining the key cost drivers, trade-offs, and potential solutions for achieving economically viable AI-powered cloud services. Additionally, we design a Viability Calculator to evaluate the economic viability of an AI compute service. Using this calculator, we conduct an analysis of common AI application deployments revealing new insights on key factors for ensuring economic viability of AI.

MAML: Towards a Faster Web in Developing Regions

2025-04-22 · 2 citations

The web experience in developing regions remains subpar, primarily due to the growing complexity of modern webpages and insufficient optimization by content providers. Users in these regions typically rely on low-end devices and limited bandwidth, which results in a poor user experience as they download and parse webpages bloated with excessive third-party CSS and JavaScript (JS). To address these challenges, we introduce the Mobile Application Markup Language (MAML), a flat layout-based web specification language that reduces computational and data transmission demands, while replacing the excessive bloat from JS with a new scripting language centered on essential (and popular) web functionalities. Last but not least, MAML is backward compatible as it can be transpiled to minimal HTML/JavaScript/CSS and thus work with legacy browsers. We benchmark MAML in terms of page load times and sizes, using a translator which can automatically port any webpage to MAML. When compared to the popular Google AMP, across 100 testing webpages, MAML offers webpage speedups by tens of seconds under challenging network conditions thanks to its significant size reductions. Next, we run a competition involving 25 university students porting 50 of the above webpages to MAML using a web-based editor we developed. This experiment verifies that, with little developer effort, MAML is quite effective in maintaining the visual and functional correctness of the originating webpages.

A review on liver cancer: Challenges, molecular insights and future directions in management

World Journal of Biology Pharmacy and Health Sciences · 2025-11-27

Liver cancer, predominantly hepatocellular carcinoma (HCC), poses a major global health challenge due to late diagnosis, poor prognosis and limited therapeutic success. Despite advances in molecular and immunological research, the complex pathogenesis and tumor microenvironment hinder effective management. This review summarizes current insights into etiology, molecular mechanisms, diagnostic limitations and therapeutic strategies, emphasizing genetic, epigenetic, viral, metabolic and environmental factors driving hepatocarcinogenesis. Recent multi-omics and liquid biopsy technologies enable early detection, biomarker discovery and personalized therapy. Precision oncology, incorporating immunotherapy, targeted agents and combination regimens, has improved outcomes, though resistance and recurrence remain challenges. Liver transplantation offers curative potential but faces donor scarcity and post-transplant complications. Emerging innovations such as molecular profiling, neoadjuvant immunotherapy and advanced drug delivery systems promise enhanced efficacy. Integrating spatial multi-omics, single-cell transcriptomics and Artificial Intelligence will refine diagnosis, prognosis and therapy, transforming liver cancer into a more manageable disease.

The Privacy Quagmire: Where Computer Scientists and Lawyers May Disagree

2025-11-17

Privacy policies dictate how systems handle user data, yet engineers struggle to verify compliance because policies use intentionally vague legal language. Current automated analyzers extract data practices using NLP but fail when policies say things like "share data for legitimate purposes" - terms that have no computational definition. This mismatch between legal flexibility and formal verification creates a fundamental barrier to automated compliance checking. We identify four systematic challenges: vague terms, evolving terminology, exception patterns that appear contradictory, and external legal dependencies. We propose an approach that preserves this ambiguity, where we use LLMs to extract structured parameters and convert them to first-order logic while keeping vague conditions as explicit placeholders for human interpretation. Our system can extract hundreds of data practices and reveals hidden complexities in TikTok and Meta policies, though the resulting formulas remain too complex for SMT solvers. This demonstrates the promise and fundamental limits of formalizing the legal text.

Self-Regulating Cars: Automating Traffic Control in Free Flow Road Networks

ArXiv.org · 2025-06-13

Free-flow road networks, such as suburban highways, are increasingly experiencing traffic congestion due to growing commuter inflow and limited infrastructure. Traditional control mechanisms, such as traffic signals or local heuristics, are ineffective or infeasible in these high-speed, signal-free environments. We introduce self-regulating cars, a reinforcement learning-based traffic control protocol that dynamically modulates vehicle speeds to optimize throughput and prevent congestion, without requiring new physical infrastructure. Our approach integrates classical traffic flow theory, gap acceptance models, and microscopic simulation into a physics-informed RL framework. By abstracting roads into super-segments, the agent captures emergent flow dynamics and learns robust speed modulation policies from instantaneous traffic observations. Evaluated in the high-fidelity PTV Vissim simulator on a real-world highway network, our method improves total throughput by 5%, reduces average delay by 13%, and decreases total stops by 3% compared to the no-control setting. It also achieves smoother, congestion-resistant flow while generalizing across varied traffic patterns, demonstrating its potential for scalable, ML-driven traffic management.