CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence

With increasing privacy concerns in artificial intelligence, regulations have mandated the right to be forgotten, granting individuals the right to withdraw their data from models. Machine unlearning has emerged as a potential solution to enable selective forgetting in models, particularly in recommender systems where historical data contains sensitive user information. Despite recent advances in recommendation unlearning, evaluating unlearning methods comprehensively remains challenging due to the absence of a unified evaluation framework and overlooked aspects of deeper influence, e.g., fairness. To address these gaps, we propose CURE4Rec, the first comprehensive benchmark for recommendation unlearning evaluation. CURE4Rec covers four aspects, i.e., unlearning Completeness, recommendation Utility, unleaRning efficiency, and recommendation fairnEss, under three data selection strategies, i.e., core data, edge data, and random data. Specifically, we consider the deeper influence of unlearning on recommendation fairness and robustness towards data with varying impact levels. We construct multiple datasets with CURE4Rec evaluation and conduct extensive experiments on existing recommendation unlearning methods. Our code is released at https://github.com/xiye7lai/CURE4Rec.

Controllable Unlearning for Image-to-Image Generative Models via $\varepsilon$-Constrained Optimization

While generative models have made significant advancements in recent years, they also raise concerns such as privacy breaches and biases. Machine unlearning has emerged as a viable solution, aiming to remove specific training data, e.g., containing private information and bias, from models. In this paper, we study the machine unlearning problem in Image-to-Image (I2I) generative models. Previous studies mainly treat it as a single objective optimization problem, offering a solitary solution, thereby neglecting the varied user expectations towards the trade-off between complete unlearning and model utility. To address this issue, we propose a controllable unlearning framework that uses a control coefficient $\varepsilon$ to control the trade-off. We reformulate the I2I generative model unlearning problem into a $\varepsilon$-constrained optimization problem and solve it with a gradient-based method to find optimal solutions for unlearning boundaries. These boundaries define the valid range for the control coefficient. Within this range, every yielded solution is theoretically guaranteed with Pareto optimality. We also analyze the convergence rate of our framework under various control functions. Extensive experiments on two benchmark datasets across three mainstream I2I models demonstrate the effectiveness of our controllable unlearning framework.

Post-Training Attribute Unlearning in Recommender Systems

With the growing privacy concerns in recommender systems, recommendation unlearning is getting increasing attention. Existing studies predominantly use training data, i.e., model inputs, as unlearning target. However, attackers can extract private information from the model even if it has not been explicitly encountered during training. We name this unseen information as \textit{attribute} and treat it as unlearning target. To protect the sensitive attribute of users, Attribute Unlearning (AU) aims to make target attributes indistinguishable. In this paper, we focus on a strict but practical setting of AU, namely Post-Training Attribute Unlearning (PoT-AU), where unlearning can only be performed after the training of the recommendation model is completed. To address the PoT-AU problem in recommender systems, we propose a two-component loss function. The first component is distinguishability loss, where we design a distribution-based measurement to make attribute labels indistinguishable from attackers. We further extend this measurement to handle multi-class attribute cases with efficient computational overhead. The second component is regularization loss, where we explore a function-space measurement that effectively maintains recommendation performance compared to parameter-space regularization. We use stochastic gradient descent algorithm to optimize our proposed loss. Extensive experiments on four real-world datasets demonstrate the effectiveness of our proposed methods.

Check, Locate, Rectify: A Training-Free Layout Calibration System for Text-to-Image Generation

Diffusion models have recently achieved remarkable progress in generating realistic images. However, challenges remain in accurately understanding and synthesizing the layout requirements in the textual prompts. To align the generated image with layout instructions, we present a training-free layout calibration system SimM that intervenes in the generative process on the fly during inference time. Specifically, following a "check-locate-rectify" pipeline, the system first analyses the prompt to generate the target layout and compares it with the intermediate outputs to automatically detect errors. Then, by moving the located activations and making intra- and inter-map adjustments, the rectification process can be performed with negligible computational overhead. To evaluate SimM over a range of layout requirements, we present a benchmark SimMBench that compensates for the lack of superlative spatial relations in existing datasets. And both quantitative and qualitative results demonstrate the effectiveness of the proposed SimM in calibrating the layout inconsistencies. Our project page is at https://simm-t2i.github.io/SimM.

Making Users Indistinguishable: Attribute-wise Unlearning in Recommender Systems

With the growing privacy concerns in recommender systems, recommendation unlearning, i.e., forgetting the impact of specific learned targets, is getting increasing attention. Existing studies predominantly use training data, i.e., model inputs, as the unlearning target. However, we find that attackers can extract private information, i.e., gender, race, and age, from a trained model even if it has not been explicitly encountered during training. We name this unseen information as attribute and treat it as the unlearning target. To protect the sensitive attribute of users, Attribute Unlearning (AU) aims to degrade attacking performance and make target attributes indistinguishable. In this paper, we focus on a strict but practical setting of AU, namely Post-Training Attribute Unlearning (PoT-AU), where unlearning can only be performed after the training of the recommendation model is completed. To address the PoT-AU problem in recommender systems, we design a two-component loss function that consists of i) distinguishability loss: making attribute labels indistinguishable from attackers, and ii) regularization loss: preventing drastic changes in the model that result in a negative impact on recommendation performance. Specifically, we investigate two types of distinguishability measurements, i.e., user-to-user and distribution-to-distribution. We use the stochastic gradient descent algorithm to optimize our proposed loss. Extensive experiments on three real-world datasets demonstrate the effectiveness of our proposed methods.

In-processing User Constrained Dominant Sets for User-Oriented Fairness in Recommender 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. The existing research on UOF is limited and fails to deal with the root cause of the UOF issue: the learning process between advantaged and disadvantaged users is unfair. To tackle this issue, we propose an In-processing User Constrained Dominant Sets (In-UCDS) framework, which is a general framework that can be applied to any backbone recommendation model to achieve user-oriented fairness. We split In-UCDS into two stages, i.e., the UCDS modeling stage and the in-processing training stage. In the UCDS modeling stage, for each disadvantaged user, we extract a constrained dominant set (a user cluster) containing some advantaged users that are similar to it. In the in-processing training stage, we move the representations of disadvantaged users closer to their corresponding cluster by calculating a fairness loss. By combining the fairness loss with the original backbone model loss, we address the UOF issue and maintain the overall recommendation performance simultaneously. Comprehensive experiments on three real-world datasets demonstrate that In-UCDS outperforms the state-of-the-art methods, leading to a fairer model with better overall recommendation performance.

Federated Unlearning via Active Forgetting

The increasing concerns regarding the privacy of machine learning models have catalyzed the exploration of machine unlearning, i.e., a process that removes the influence of training data on machine learning models. This concern also arises in the realm of federated learning, prompting researchers to address the federated unlearning problem. However, federated unlearning remains challenging. Existing unlearning methods can be broadly categorized into two approaches, i.e., exact unlearning and approximate unlearning. Firstly, implementing exact unlearning, which typically relies on the partition-aggregation framework, in a distributed manner does not improve time efficiency theoretically. Secondly, existing federated (approximate) unlearning methods suffer from imprecise data influence estimation, significant computational burden, or both. To this end, we propose a novel federated unlearning framework based on incremental learning, which is independent of specific models and federated settings. Our framework differs from existing federated unlearning methods that rely on approximate retraining or data influence estimation. Instead, we leverage new memories to overwrite old ones, imitating the process of \textit{active forgetting} in neurology. Specifically, the model, intended to unlearn, serves as a student model that continuously learns from randomly initiated teacher models. To preserve catastrophic forgetting of non-target data, we utilize elastic weight consolidation to elastically constrain weight change. Extensive experiments on three benchmark datasets demonstrate the efficiency and effectiveness of our proposed method. The result of backdoor attacks demonstrates that our proposed method achieves satisfying completeness.

Selective and Collaborative Influence Function for Efficient Recommendation Unlearning

Recent regulations on the Right to be Forgotten have greatly influenced the way of running a recommender system, because users now have the right to withdraw their private data. Besides simply deleting the target data in the database, unlearning the associated data lineage e.g., the learned personal features and preferences in the model, is also necessary for data withdrawal. Existing unlearning methods are mainly devised for generalized machine learning models in classification tasks. In this paper, we first identify two main disadvantages of directly applying existing unlearning methods in the context of recommendation, i.e., (i) unsatisfactory efficiency for large-scale recommendation models and (ii) destruction of collaboration across users and items. To tackle the above issues, we propose an extra-efficient recommendation unlearning method based on Selective and Collaborative Influence Function (SCIF). Our proposed method can (i) avoid any kind of retraining which is computationally prohibitive for large-scale systems, (ii) further enhance efficiency by selectively updating user embedding and (iii) preserve the collaboration across the remaining users and items. Furthermore, in order to evaluate the unlearning completeness, we define a Membership Inference Oracle (MIO), which can justify whether the unlearned data points were in the training set of the model, i.e., whether a data point was completely unlearned. Extensive experiments on two benchmark datasets demonstrate that our proposed method can not only greatly enhance unlearning efficiency, but also achieve adequate unlearning completeness. More importantly, our proposed method outperforms the state-of-the-art unlearning method regarding comprehensive recommendation metrics.

VoP: Text-Video Co-operative Prompt Tuning for Cross-Modal Retrieval

Many recent studies leverage the pre-trained CLIP for text-video cross-modal retrieval by tuning the backbone with additional heavy modules, which not only brings huge computational burdens with much more parameters, but also leads to the knowledge forgetting from upstream models.In this work, we propose the VoP: Text-Video Co-operative Prompt Tuning for efficient tuning on the text-video retrieval task. The proposed VoP is an end-to-end framework with both video & text prompts introducing, which can be regarded as a powerful baseline with only 0.1% trainable parameters. Further, based on the spatio-temporal characteristics of videos, we develop three novel video prompt mechanisms to improve the performance with different scales of trainable parameters. The basic idea of the VoP enhancement is to model the frame position, frame context, and layer function with specific trainable prompts, respectively. Extensive experiments show that compared to full fine-tuning, the enhanced VoP achieves a 1.4% average R@1 gain across five text-video retrieval benchmarks with 6x less parameter overhead. The code will be available at https://github.com/bighuang624/VoP.

Making Recommender Systems Forget: Learning and Unlearning for Erasable Recommendation

Privacy laws and regulations enforce data-driven systems, e.g., recommender systems, to erase the data that concern individuals. As machine learning models potentially memorize the training data, data erasure should also unlearn the data lineage in models, which raises increasing interest in the problem of Machine Unlearning (MU). However, existing MU methods cannot be directly applied into recommendation. The basic idea of most recommender systems is collaborative filtering, but existing MU methods ignore the collaborative information across users and items. In this paper, we propose a general erasable recommendation framework, namely LASER, which consists of Group module and SeqTrain module. Firstly, Group module partitions users into balanced groups based on their similarity of collaborative embedding learned via hypergraph. Then SeqTrain module trains the model sequentially on all groups with curriculum learning. Both theoretical analysis and experiments on two real-world datasets demonstrate that LASER can not only achieve efficient unlearning, but also outperform the state-of-the-art unlearning framework in terms of model utility.