Machine unlearning, as a post-hoc processing technique, has gained widespread adoption in addressing challenges like bias mitigation and robustness enhancement. However, existing non-privacy unlearning-based solutions persist in using a binary data removal framework designed for privacy-driven motivation, even when repurposed for fairness or robustness improvements. This leads to significant utility loss, a phenomenon known as “over-unlearning”. While over-unlearning has been largely described in many studies as primarily causing utility degradation, we investigate deeper insights in this work through counterfactual leave-one-out analysis. Based on insights, we introduce a soft weighting strategy that assigns tailored weights to each sample by solving a convex quadratic programming problem analytically, which enables fine-grained model adjustments to address the over-unlearning. We demonstrate that the proposed soft-weighted scheme can be seamlessly integrated into most existing unlearning algorithms. Extensive experiments show that in fairness- and robustness-driven tasks, the soft-weighted scheme significantly outperforms hard-weighted schemes in fairness/robustness metrics and alleviates the decline in utility metric, thereby enhancing unlearning algorithm as an effective correction solution.

To protect clients' right to be forgotten in federated learning, federated unlearning aims to remove the data contribution of leaving clients from the global learned model. While current studies mainly focused on enhancing unlearning efficiency and effectiveness, the crucial aspects of efficiency fairness and performance fairness among decentralized clients during unlearning have remained largely unexplored. In this study, we introduce FedShard, the first federated unlearning algorithm designed to concurrently guarantee both efficiency fairness and performance fairness. FedShard adaptively addresses the challenges introduced by dilemmas among convergence, unlearning efficiency, and unlearning fairness. Furthermore, we propose two novel metrics to quantitatively assess the fairness of unlearning algorithms, which we prove to satisfy well-known properties in other existing fairness measurements. Our theoretical analysis and numerical evaluation validate FedShard's fairness in terms of both unlearning performance and efficiency. We demonstrate that FedShard mitigates unfairness risks such as cascaded leaving and poisoning attacks and realizes more balanced unlearning costs among clients. Experimental results indicate that FedShard accelerates the data unlearning process 1.3-6.2 times faster than retraining from scratch and 4.9 times faster than the state-of-the-art exact unlearning methods.

Machine unlearning has gained increasing attention in recent years, as a promising technique to selectively remove unwanted privacy or copyrighted information from Large Language Models that are trained on a massive scale of human data.However, the emergence of Large Reasoning Models (LRMs), which emphasize long chain-of-thought (CoT) reasoning to address complex questions, presents a dilemma to unlearning: existing methods either struggle to completely eliminate undesired knowledge from the CoT traces or degrade the reasoning performances due to the interference with the reasoning process.To this end, we introduce Counterfactual Unlearning through iterative Preference Optimization (CiPO), a novel framework that redefines unlearning as the targeted intervention of the CoT reasoning in LRMs.More specifically, given a desired unlearning target answer, CiPO instructs LRMs to generate a logically valid counterfactual reasoning trace for preference tuning.As the LRM adjusts to the counterfactual trace, CiPO iteratively updates the preference learning data to increase the discrepancy from the original model.This iterative loop ensures both desirable unlearning and smooth optimization, effectively mitigating the dilemma.Experiments on challenging benchmarks demonstrate that CiPO excels at unlearning, completely removing knowledge from both the intermediate CoT steps and the final answer, while preserving the reasoning abilities of LRMs. 1

Vector data trading is essential for cross-domain learning with vector databases, yet it remains largely unexplored. We study this problem under online learning, where sellers face uncertain retrieval costs and buyers provide stochastic feedback to posted prices. Three main challenges arise: (1) heterogeneous and partial feedback in configuration learning, (2) variable and complex feedback in pricing learning, and (3) inherent coupling between configuration and pricing decisions. We propose a hierarchical bandit framework that jointly optimizes retrieval configurations and pricing. Stage I employs contextual clustering with confidence-based exploration to learn effective configurations with logarithmic regret. Stage II adopts interval-based price selection with local Taylor approximation to estimate buyer responses and achieve sublinear regret. We establish theoretical guarantees with polynomial time complexity and validate the framework on four real-world datasets, demonstrating consistent improvements in cumulative reward and regret reduction compared with existing methods.

Proximity graphs are the state-of-the-art solution for approximate nearest neighbor (ANN) search, supporting applications such as Web search and retrieval-augmented generation (RAG). Sustaining long-term performance requires adaptive pruning as data and query workloads evolve. However, existing approaches are largely static and uniform. Adaptive pruning faces three key challenges: temporal drift in data and query distributions, spatial heterogeneity across graph regions, and costly feedback due to graph-level evaluations. We present BANCO, a bandit-based framework for adaptive proximity graph pruning. BANCO unifies diverse pruning strategies within a common decision space and optimizes them via a drift-aware batched bandit algorithm. It addresses temporal drift through drift-aware updates, captures spatial heterogeneity using contextual features for region-specific pruning, and reduces evaluation costs through batched feedback aggregation. We establish a dynamic regret bound with sublinear loss and polynomial computational complexity. Extensive experiments on four real-world datasets demonstrate that BANCO helps maintain long-term ANN search efficiency and accuracy under evolving data and workloads.

In the bigdata era, data trading significantly enhances data-driven decision-making by facilitating data sharing. Streaming data from sources such as mobile devices and social media platforms creates new opportunities and challenges for data trading. Traditional data trading methods, designed for one time queries over static data base snapshots, neglect the growing need for trading continuous queries over streaming data. If applied directly to continuous queries, existing methods often result in repeated and imprecise charges that reduce the seller's profit, as they do not consider computation sharing during continuous query execution. To address these challenges, we propose CQ Trade, the first mechanism for continuous query based data trading, which incorporates computation sharing in query execution and integrates seamlessly with existing trading mechanisms. Our contributions are threefold: (1) we provide a theoretical analysis of prevalent computation-sharing techniques, including costmodeling and closed-form computation-sharing strategy derivation; (2) we formulate a general optimization problem to maximize the seller's profit, adaptable to various computation-sharing techniques; (3) we identify that our op timization problem merges vector bin packing and multidimensional knapsack challenges, and we tackle this complexity with a tailored branch-and-price algorithm that decomposes the problem in to a master problem and multiple sub-problems, achieving a globally optimal solution. Evaluation shows CQ Trade improve strading success rate by 12.8% and increases seller profit by 28.7% compared to traditional methods.

Data trading significantly enhances data utility by enabling data sharing across diverse applications. Despite being crucial for real-time analytics and online machine learning, trading continuous queries with streaming data output remains largely unexplored. The inherent characteristics of trading continuous queries pose distinctive technical challenges in scheduling query execution. First, the streaming nature demands online scheduling under information uncertainty, where data utilities and execution costs vary unpredictably during query execution. Second, the intrinsic NP-hardness of the optimization problem, coupled with repeated invocation requirements, necessitates efficient algorithmic solutions to address computational complexity. We present OSTOR, the first online scheduling framework for trading continuous queries. OSTOR aims to maximize social welfare, defined as the difference between buyers' obtained utilities and sellers' execution costs, while achieving both theoretical guarantees and practical efficiency. To handle the information uncertainty, we present a primary-dual decomposition method that transforms the online scheduling problem into multiple one-round integer programming problems, enabling adaptive decision-making that only needs current system information. To address the computational complexity, we design an adaptive dual descent (ADD) algorithm that iteratively optimizes dual variables, achieving a bounded constant approximation ratio in polynomial time. We further enhance OSTOR through structureaware greedy optimization strategies with provable performance guarantees. Extensive experiments demonstrate that OSTOR substantially improves social welfare and reduces query execution costs on both real-world and synthetic datasets, compared to existing data trading methods.

Federated learning protects users’ data privacy by sharing users’ local model parameters (instead of raw data) with a server. However, when massive users train a large machine learning model through federated learning, the dynamically varying and often heavy communication overhead can put significant pressure on the network operator. The operator may choose to dynamically change the network prices in response, which will eventually affect the payoffs of the server and users. This paper considers the under-explored yet important issue of the joint design of participation incentives (for encouraging users’ contribution to federated learning) and network pricing (for managing network resources). Due to heterogeneous users’ private information and multi-dimensional decisions, the optimization problems in Stage I of multi-stage games are non-convex. Nevertheless, we are able to analytically derive the corresponding optimal contract and pricing mechanism through proper transformations of constraints, variables, and functions, under three interaction structures of the participants. We show that the coordinated structure is better than the two uncoordinated structures, as it avoids the selfish behaviors of the network operator and the server; the vertically uncoordinated structure is better than the horizontally uncoordinated structure, as it avoids the interests misalignment between the server and the network operator. We also propose multi-period network pricing to reduce the implementation complexity of dynamic pricing. Numerical results based on real-world datasets show that our proposed mechanisms decrease the server's cost by up to 24.87% and increase the network operator's profit by up to 1245.25%, compared with the state-of-the-art benchmarks.

To protect users'right to be forgottenin federated learning, federated unlearning aims at eliminating the impact of leaving users' data on the global learned model. The current research in federated unlearning mainly concentrates on developing effective and efficient unlearning techniques. However, the issue of incentivizing valuable users to remain engaged and preventing their data from being unlearned is still under-explored, yet important to the unlearned model performance. This paper focuses on the incentive issue and develops an incentive mechanism for federated learning and unlearning. We first characterize the leaving users' impact on the global model accuracy and the required communication rounds for unlearning. Building on these results, we propose a four-stage game to capture the interaction and information updates during the learning and unlearning process. A key contribution is to summarize users' multi-dimensional private information into one-dimensional metrics to guide the incentive design. Interestingly, we prove that allowing federated unlearning can result in reduced payoffs for both the server and users, compared to a scenario without unlearning. Numerical results demonstrate the necessity of unlearning incentives for retaining valuable leaving users, and also show that our proposed mechanisms decrease the server's cost by up to 53.91% compared to state-of-the-art benchmarks.

In the era of big data, data trading significantly enhances data-driven technologies by facilitating data sharing. Despite the clear advantages often experienced by data users when incorporating multiple sources, the topic of multi-source data trading remains largely unexplored. This paper designs a novel data trading framework, which enables multi-source data trading through multi-source cooperation. The proposed framework aims to improve data usage efficiency and increase seller revenue. In particular, we model data sellers’ cooperative decisions through the Nash bargaining framework and systematically outline the interactions between sellers and buyers as a two-stage Stackelberg game. A key contribution of this work is the consideration of coupling among diverse data products, which is essential but often overlooked in prior studies. We properly classify data’s utility into endogenous and relational categories to disentangle the coupling. Despite the inherent non-convex nature of the optimization problem, we methodically derive the closed-form optimal solutions by decomposing the problem into several subproblems. Interestingly, we reveal that, under our proposed framework, sellers’ revenue initially remains steady with the increase of product coupling level, but begins to rise once the level exceeds a certain threshold due to the substitute effect. Finally, experimental results show that our proposed framework can improve the seller’s profit by up to 46.32% compared to traditional data trading methods in the current data market.

By allowing users to erase their data’s impact on federated learning models, federated unlearning protects users’ right to be forgotten and data privacy. Despite a burgeoning body of research on federated unlearning’s technical feasibility, there is a paucity of literature investigating the considerations behind users’ requests for data revocation. This paper proposes a non-cooperative game framework to study users’ data revocation strategies in federated unlearning. We prove the existence of a Nash equilibrium. However, users’ best response strategies are coupled via model performance and unlearning costs, which makes the equilibrium computation challenging. We obtain the Nash equilibrium by establishing its equivalence with a much simpler auxiliary optimization problem. We also summarize users’ multi-dimensional attributes into a single-dimensional metric and derive the closed-form characterization of an equilibrium, when users’ unlearning costs are negligible. Moreover, we compare the cases of allowing and forbidding partial data revocation in federated unlearning. Interestingly, the results reveal that allowing partial revocation does not necessarily increase users’ data contributions or payoffs due to the game structure. Additionally, we demonstrate that positive externalities may exist between users’ data revocation decisions when users incur unlearning costs, while this is not the case when their unlearning costs are negligible.

Federated learning protects users’ data privacy though sharing users’ local model parameters (instead of raw data) with a server. However, when massive users train a large machine learning model through federated learning, the dynamically varying and often heavy communication overhead can put significant pressure on the network operator. The operator may choose to dynamically change the network prices in response, which will eventually affect the payoffs of the server and users. This paper considers the under-explored yet important issue of the joint design of participation incentives (for encouraging users’ contribution to federated learning) and network pricing (for managing network resources). Due to heterogeneous users’ private information and multi-dimensional decisions, the optimization problems in Stage I of multi-stage games are non-convex. Nevertheless, we are able to analytically derive the corresponding optimal contract and pricing mechanism through proper transformations of constraints, variables, and functions, under both vertical and horizontal interaction structures of the participants. We show that the vertical structure is better than the horizontal one, as it avoids the interests misalignment between the server and the network operator. Numerical results based on real-world datasets show that our proposed mechanisms decrease server’s cost by up to 24.87% comparing with the state-of-the-art benchmarks.

To protect users' right to be forgotten in federated learning, federated unlearning aims at eliminating the impact of leaving users' data on the global learned model. The current research in federated unlearning mainly concentrated on developing effective and efficient unlearning techniques. However, the issue of incentivizing valuable users to remain engaged and preventing their data from being unlearned is still under-explored, yet important to the unlearned model performance. This paper focuses on the incentive issue and develops an incentive mechanism for federated learning and unlearning. We first characterize the leaving users' impact on the global model accuracy and the required communication rounds for unlearning. Building on these results, we propose a four-stage game to capture the interaction and information updates during the learning and unlearning process. A key contribution is to summarize users' multi-dimensional private information into one-dimensional metrics to guide the incentive design. We show that users who incur high costs and experience significant training losses are more likely to discontinue their engagement through federated unlearning. The server tends to retain users who make substantial contributions to the model but has a trade-off on users' training losses, as large training losses of retained users increase privacy costs but decrease unlearning costs. The numerical results demonstrate the necessity of unlearning incentives for retaining valuable leaving users, and also show that our proposed mechanisms decrease the server's cost by up to 53.91% compared to state-of-the-art benchmarks.

An Internet of Things (IoT) system can include several different types of service providers, who sell IoT service, network service, and computation service to customers, either jointly or separately. A deep understanding of complicated coupling among these providers in terms of pricing and service decisions is critical to the success of IoT networks. This paper studies the impact of the provider interaction structures on the overall IoT system with heterogeneous customers. Specifically, we first study a generic IoT scenario with three interaction structures: coordinated, vertically-uncoordinated, and horizontally-uncoordinated structures. Despite the challenging non-convex optimization problems involved in modeling and analyzing these structures, we successfully obtain the closed-form optimal pricing strategies of providers in each interaction structure. We further extend the analysis to a specific IoT scenario with local computation capability (e.g., Internet of Vehicles (IoV)). We prove that the coordinated structure is better than two uncoordinated structures for both providers and customers, as it avoids selfish price markup behaviors in uncoordinated structures. Between the two uncoordinated structures, when customers' demand variance is large and utility-cost ratio is medium, vertically-uncoordinated structure is better than horizontal one for both providers and customers, due to the complementary providers' competition in horizontally-uncoordinated structure. Counter-intuitively, we identify that providers' optimal prices do not change with their costs at the critical point of customers' full participation in the vertically-uncoordinated structure.

An Internet of Things (IoT) system can include several different types of service providers, who sell IoT service, network service, and computation service to customers, either jointly or separately. The complicated coupling among these providers in terms of pricing and service decisions is an under-explored research area, the understanding of which is critical to the success of IoT networks. This paper studies the impact of the provider interaction structures on the overall IoT system with massive heterogeneous customers. Specifically, we consider three interaction structures: coordinated, vertically-uncoordinated, and horizontally-uncoordinated structures. Despite the challenging non-convex optimization problems involved in modeling and analyzing these structures, we successfully obtain the closed-form optimal pricing strategies of providers in each interaction structure. We prove that the coordinated structure is better than two uncoordinated structures for both providers and customers, as it avoids selfish price markup behaviors in uncoordinated structures. When customers’ demand variance is large and utility-cost ratio is medium, vertically-uncoordinated structure is better than horizontal one for both providers and customers, due to the complementary providers’ competition in horizontally-uncoordinated structure. Counter-intuitively, we identify that providers’ optimal prices do not change with their costs at the critical point of customers’ full participation in the vertically-uncoordinated structure.

A distributed machine learning platform needs to recruit many heterogeneous worker nodes to finish computation simultaneously. As a result, the overall performance may be degraded due to straggling workers. By introducing redundancy into computation, coded machine learning can effectively improve the runtime performance by recovering the final computation result through the first k (out of the total n) workers who finish computation. While existing studies focus on designing efficient coding schemes, the issue of designing proper incentives to encourage worker participation is still under-explored. This paper studies the platform's optimal incentive mechanism for motivating proper workers' participation in coded machine learning, despite the incomplete information about heterogeneous workers' computation performances and costs. A key contribution of this work is to summarize workers' multi-dimensional heterogeneity as a one-dimensional metric, which guides the platform's efficient selection of workers under incomplete information with a linear computation complexity. Moreover, we prove that the optimal recovery threshold k is linearly proportional to the participator number n if we use the widely adopted MDS codes for data encoding. We also show that the platform's increased cost due to incomplete information disappears when worker number is sufficiently large, but it does not monotonically decrease in worker number.

A distributed machine learning platform needs to recruit many heterogeneous worker nodes to finish computation simultaneously. As a result, the overall performance may be degraded due to straggling workers. By introducing redundancy into computation, coded machine learning can effectively improve the runtime performance by recovering the final computation result through the first k (out of the total n) workers who finish computation. While existing studies focus on designing efficient coding schemes, the issue of designing proper incentives to encourage worker participation is still under-explored. This paper studies the platform's optimal incentive mechanism for motivating proper workers' participation in coded machine learning, despite the multi-dimensional incomplete information about heterogeneous workers' computation performances and costs. A key contribution of this work is to summarize workers' multi-dimensional heterogeneity as a one-dimensional metric, which guides the platform's efficient selection of workers under incomplete information with a linear computation complexity. Although the exact overall runtime is intractable, we characterize the platform's (asymptotically) optimal load assignment to heterogeneous workers in coded machine learning. When the platform has incomplete information about workers' costs, it is optimal to assign loads only based on workers' computation performances; when the platform further lacks workers' computation performance information, it is optimal to design the loads to be cost-dependent and performance-dependent.

As an emerging machine learning technique, federated learning has received significant attention recently due to its promising performance in mitigating privacy risks and costs. While most of the existing work of federated learning focused on designing learning algorithm to improve training performance, the incentive issue for encouraging users' participation is still under-explored. This paper presents an analytical study on the server's optimal incentive mechanism design, in the presence of users' multi-dimensional private information (e.g., training cost and communication delay). Specifically, we consider a multi-dimensional contract-theoretic approach, with a key contribution of summarizing users' multi-dimensional private information into a one-dimensional criterion that allows a complete order of users. We further perform the analysis in three information scenarios to reveal the impact of information asymmetry levels on server's optimal strategy and minimum cost. We show that weakly incomplete information does not increase the server's cost (comparing with the complete information scenario) when training data is IID, but it in general does when data is non-IID. Furthermore, the optimal mechanism design under strongly incomplete information is much more challenging, and it is not always optimal for the server to incentivize the group of users with the lowest training cost and delay to participate.

Sharing platforms have facilitated the redistribution of underused resources by providing convenient online marketplaces for individual sellers and buyers. However, the sellers on these platforms may not fully disclose the information of their shared commodities, due to strategic behaviors or privacy concerns. Sellers' strategic information disclosure significantly affects buyers' user experiences and platforms' reputation. This paper presents one of the first analytical studies on information disclosure and pricing strategies of competing sellers on a sharing platform. In particular, we propose a three-stage game framework to capture sellers' strategic behaviors and buyers' decisions. Although the corresponding optimization problem is non-convex, we are able to completely characterize the complex market equilibria. We demonstrate that full disclosure by all sellers or non-disclosure by all sellers will both lead to intense price competition. We prove that the former all-disclosure case is never an equilibrium even when all sellers have good commodity qualities and low privacy costs, while the latter non-disclosure case can be an equilibrium under which all sellers get zero profit. Interestingly, we also reveal that buyers' estimation biases encourage information disclosure as they mitigate the competition among sellers.