The value and copyright of training data are crucial in the artificial intelligence industry. Service platforms should protect data providers' legitimate rights and fairly reward them for their contributions. Shapley value, a potent tool for evaluating contributions, outperforms other methods in theory, but its computational overhead escalates exponentially with the number of data providers. Recent studies on Shapley values have proposed various approximation algorithms to address the computational complexity issues inherent in exact calculations. However, they need to retrain for each test sample, leading to intolerable costs. We propose Fast-DataShapley, a one-pass training framework that leverages the weighted least squares characterization of the Shapley value to train a reusable explainer model with real-time reasoning speed. Given new test samples, no retraining is required to calculate the Shapley values of the training data. Additionally, we propose three methods with theoretical guarantees to reduce training overhead from two aspects: the approximate calculation of the utility function and the reduction of the sample space complexity. We analyze time complexity to show the efficiency of our methods. The experimental evaluations on various image datasets demonstrate superior performance and efficiency compared to baselines. Specifically, the performance is improved to more than 2×, and the explainer's training speed can be increased by two orders of magnitude.

LLM-powered agents are evolving from passive recommenders into autonomous executors, leveraging tools via the Model Context Protocol (MCP) for web automation. However, this paradigm introduces a new vulnerability: tool poisoning attacks that manipulate the MCP context can corrupt an agent's reasoning. Existing methods focus on anomaly detection and lack autonomous correction mechanisms, hindering their real-world deployment.

High-quality data labeling is essential for training robust machine learning models; however, existing methods often ignore fraud or assume non-negative worker utility, failing to penalize harmful contributions without discouraging participation. To address this, we propose the Negativity-Aware Incentive (NAI) mechanism which introduces two novel components. First, the Ability-Result Characteristic Function (AR-CF) adapts and extends Shapley value theory through signed valuation to explicitly capture both positive and negative contributions, by combining workers' abilities with real-time task results to define contribution values. Second, a dynamic stake pool mechanism employs pre-commitment economics with adaptive dual-control parameters to balance fairness and operational efficiency. Through extensive experiments on multimodal datasets (images, text, audio, video), NAI outperforms state-of-the-art baselines: it improves video labeling accuracy by 16.6%, and reduces fraudulent behaviors by 33.9%. Furthermore, our deployment on the NetEase Youling crowdsourcing platform, serving 430,000 registered workers with 80,000 monthly active workers, validates NAI's real-world viability. Real-time A/B testing shows a 59.6% improvement in labeling quality for beginner tasks and a consistent reduction in fraud rates (14.8%-33.9%) across difficulty levels. This work establishes a paradigm shift in crowdsourcing system design, demonstrating that explicit negative modeling can enhance data quality, optimize costs, and foster participation at scale.

Time series forecasting with exogenous variables is a critical emerging paradigm that presents unique challenges in modeling dependencies between variables. Traditional models often struggle to differentiate between endogenous and exogenous variables, leading to inefficiencies and overfitting. In this paper, we introduce CrossLinear, a novel Linear-based forecasting model that addresses these challenges by incorporating a plug-and-play cross-correlation embedding module. This lightweight module captures the dependencies between variables with minimal computational cost and seamlessly integrates into existing neural networks. Specifically, it captures time-invariant and direct variable dependencies while disregarding time-varying or indirect dependencies, thereby mitigating the risk of overfitting in dependency modeling and contributing to consistent performance improvements. Furthermore, CrossLinear employs patch-wise processing and a global linear head to effectively capture both short-term and long-term temporal dependencies, further improving its forecasting precision. Extensive experiments on 12 real-world datasets demonstrate that CrossLinear achieves superior performance in both short-term and long-term forecasting tasks. The ablation study underscores the effectiveness of the cross-correlation embedding module. Additionally, the generalizability of this module makes it a valuable plug-in for various forecasting tasks across different domains. Codes are available at https://github.com/mumiao2000/CrossLinear.

The diverse advertiser demands (brand effects or immediate outcomes) lead to distinct selling (pre-agreed volumes with an under-delivery penalty or compete per auction) and pricing (fixed prices or varying bids) patterns in Guaranteed delivery (GD) and real-time bidding (RTB) advertising. This necessitates fair impression allocation to unify the two markets for promoting ad content diversity and overall revenue. Existing approaches often deprive RTB ads of equal exposure opportunities by prioritizing GD ads, and coarse-grained methods are inferior to 1) Ambiguous reward due to varied objectives and constraints of GD fulfillment and RTB utility, hindering measurement of each allocation's contribution to the global interests; 2) Intensified competition by the coexistence of GD and RTB ads, complicating their mutual relationships; 3) Policy degradation caused by evolving user traffic and bid landscape, requiring adaptivity to distribution shifts.

User impression forecasting underpins various commercial activities, from long-term strategic decisions to short-term automated operations. As a representative that involves both kinds, the highly profitable Guaranteed Delivery (GD) advertising focuses mainly on promoting brand effect by allowing advertisers to order target impressions weeksin advance and get allocatedonline at the scheduled time. Such a business mode naturally incurs three issues making existing solutions inferior: 1) Timescale-granularity dilemma of coherently supporting the sales of day-level impressions of the distant future and the corresponding fine-grained allocation in real-time. 2) High dimensionality due to the Cartesian product of user attribute combinations. 3) Stability-plasticity dilemma of instant adaptation to emerging patterns of temporal dependency withoutcatastrophic forgetting of repeated ones facing the non-stationary traffic.

Many data applications can be facilitated or even spawned by joint analysis on databases held by different owners, but privacy concerns are currently the biggest hindrance. Though a practical privacy-preserving collaborative database analytics system is strongly desired, existing approaches do not support efficient queries for several essential SQL operators such as the general join, especially on large databases. In this paper, we propose, analyze, and implement Scape, a Scalable Collaborative Analytics system on Private databasE with malicious security. In Scape, databases from different parties are secretly shared to three non-colluding computing parties. Users can perform various SQL queries (including fully functional Join, Group by, Aggregation, etc.) on shared databases, and all entities learn nothing beyond their priori knowledge during the whole execution even when they deviate from protocols. At the heart of Scape lies several asymptotically efficient SQL protocols. Particularly, our general join protocol has O (n log2n + m) communication/computation cost when joining two tables with o (n) rows to a table with 0 (m) rows, significantly outperforming the state-of-the-art approach with O(n2) cost. The benchmark results confirm the advantages of Scape, which is up to 25 x faster than the baseline.

Data annotation has been a key boost for the artificial intelligence. However, difficult tasks such as fine-grained classification need lots of labeled data to train a feasible model. On the one hand, using people who have expert knowledge on the datasets to annotate all data can be costly. On the other hand, amateurs are cheaper but not able to give precise labels. Related works like machine labeling need labeled data to start up. Crowd-Model labeling can hardly solve complex tasks like fine-grained classification. Lately, combining domain experts and cost-effective crowd to solve complex tasks has become an area of increasing interest in research and industry. However, most works rarely investigate the cost gap between experts and amateurs and see how it influences the final annotation cost. In this paper, we combine both experts and amateurs to build a cost-effective data annotation system called COCA. COCA annotates the target dataset from scratch and save costs by our annotation assignment strategy. Extensive evaluations show that when reaching the same precision, COCA can reach a lower cost than SOTA automatic labeling models when the ratio of expert price to amateur price is above a certain value.

Guaranteed delivery (GD) and real-time bidding (RTB) constitute two parallel profit streams for the publisher. The diverse advertiser demands (brand or instant effect) result in different selling (in bulk or via auction) and pricing (fixed unit price or various bids) patterns, which naturally raises the fusion allocation issue of breaking the two markets' barrier and selling out at the global highest price boosting the total revenue. The fusion process complicates the competition between GD and RTB, and GD contracts with overlapping targeting. The non-stationary user traffic and bid landscape further worsen the situation, making the assignment unsupervised and hard to evaluate. Thus, a static policy or coarse-grained modeling from existing work is inferior to facing the above challenges.

Labeling data (e.g., labeling the people, objects, actions, and scene in images) comprehensively and efficiently is a widely needed but challenging task. Numerous models were proposed to label various data and many approaches were designed to enhance the ability of deep learning models or accelerate them. Unfortunately, a single machine-learning model is not powerful enough to extract various semantic information from data. Given certain applications, such as image retrieval platforms and photo album management apps, it is often required to execute a collection of models to obtain sufficient labels. With limited computing resources and stringent delay, given a data stream and a collection of applicable resource-hungry deep-learning models, we design a novel approach to adaptively schedule a subset of these models to execute on each data item, aiming to maximize the value of the model output (e.g., the number of high-confidence labels). Achieving this lofty goal is nontrivial since a model’s output on any data item is content-dependent and unknown until we execute it. To tackle this, we propose an Adaptive Model Scheduling framework, consisting of (1) a deep reinforcement learning-based approach to predict the value of unexecuted models by mining semantic relationship among diverse models, and (2) two heuristic algorithms to adaptively schedule the model execution order under a deadline or deadline-memory constraints, respectively. The proposed framework does not require any prior knowledge of the data, which works as a powerful complement to existing model optimization technologies. We conduct extensive evaluations on five diverse image datasets and 30 popular image labeling models to demonstrate the effectiveness of our design: our design could save around 53% execution time without loss of any valuable labels.

Federated learning (FL) enables large amounts of participants to construct a global learning model, while storing training data privately at each client device. A fundamental issue in this framework is the susceptibility to the erroneous training data. This problem is especially challenging due to the invisibility of clients' local training data and training process, as well as the resource constraints of a large number of mobile and edge devices. In this paper, we try to tackle this challenging issue by introducing the first FL debugging framework, FLDebugger, for mitigating test error caused by erroneous training data. The pro-posed solution traces the global model's bugs (test errors), jointly through the training log and the underlying learning algorithm, back to first identify the clients and subsequently their training samples that are most responsible for the errors. In addition, we devise an influence-based participant selection strategy to fix bugs as well as to accelerate the convergence of model retraining. The performance of the identification algorithm is evaluated via extensive experiments on a real AIoT system (50 clients, including 20 edge computers, 20 laptops and 10 desktops) and in larger-scale simulated environments. The evaluation results attest to that our framework achieves accurate and efficient identification of negatively influential clients and samples, and significantly improves the model performance by fixing bugs.

Labeling data comprehensively and efficiently is a widely needed but challenging task. With limited computing resources, given a data stream and a collection of deep-learning models, we propose to adaptively select and schedule a subset of these models to execute, aiming to maximize the value of the model output. Achieving this goal is nontrivial since a model's output on any data item is content-dependent and hard to predict. In this paper, we present an Adaptive Model Scheduling framework, consisting of 1) a deep reinforcement learning-based approach to predict the value of unexecuted models by mining semantic relationship among diverse models, and 2) two heuristic algorithms to adaptively schedule models under deadline or deadline-memory constraints. The proposed framework does not require any prior knowledge of the data, which works as a powerful complement to existing model optimization technologies. We conduct extensive evaluations on 30 popular image labeling models to demonstrate the effectiveness of our design.

Bloom filter is effective, space-efficient data structure for concisely representing a data set and supporting approximate membership queries. Traditionally, researchers often believe that it is possible that a Bloom filter returns a false positive, but it will never return a false negative under well-behaved operations. By investigating the mainstream variants, however, we observe that a Bloom filter does return false negatives in many scenarios. In this work, we show that the undetectable incorrect deletion of false positive items and detectable incorrect deletion of multiaddress items are two general causes of false negative in a Bloom filter. We then measure the potential and exposed false negatives theoretically and practically. Inspired by the fact that the potential false negatives are usually not fully exposed, we propose a novel Bloom filter scheme, which increases the ratio of bits set to a value larger than one without decreasing the ratio of bits set to zero. Mathematical analysis and comprehensive experiments show that this design can reduce the number of exposed false negatives as well as decrease the likelihood of false positives. To the best of our knowledge, this is the first work dealing with both the false positive and false negative problems of Bloom filter systematically when supporting standard usages of item insertion, query, and deletion operations.

% '& ( " ) * ,+ .-/0 ,1 ,+ 2 0 " 3 ,4 5 76 8 :9 ; 6 =< > (4 ?A@ B? BC D9 E F G; H I J? AK L6 8 NM F 0K L6 8