Recommender systems are widely required and deployed to address real-world problems. In this paper, we study a new yet challenging real-world setting for recommender systems, where only user browsing histories are available without any explicit feedback. No item acquisition information, e.g., purchasing or rating, is given. By assuming that user browsing sequences are likely to contain the items to acquire, we draw an analogy to the setting of partial label learning in weakly supervised learning. This enables us to train reliable recommender systems only using browsing histories. We term the proposed method as Partial Acquisition Recommender System (PARS). Empirical results on real-world benchmark datasets show the effectiveness of the proposed method. Surprisingly, we also show that the proposed method even surpasses some baselines using item acquisition information.

Zichuan Fu, Xian Wu, Yejing Wang, Wanyu Wang, Shanshan Ye, Hongzhi Yin, Yi Chang, Yefeng Zheng, Xiangyu Zhao. Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2025.

Neural Architecture Search (NAS) has emerged as a powerful approach for automating neural network design. However, existing NAS methods face critical limitations in real-world deployments: architectures lack adaptability across scenarios, each deployment context requires costly separate searches, and performance consistency across diverse platforms remains challenging. We propose DANCE (Dynamic Architectures with Neural Continuous Evolution), which reformulates architecture search as a continuous evolution problem through learning distributions over architectural components. DANCE introduces three key innovations: a continuous architecture distribution enabling smooth adaptation, a unified architecture space with learned selection gates for efficient sampling, and a multi-stage training strategy for effective deployment optimization. Extensive experiments across five datasets demonstrate DANCE's effectiveness. Our method consistently outperforms state-of-the-art NAS approaches in terms of accuracy while significantly reducing search costs. Under varying computational constraints, DANCE maintains robust performance while smoothly adapting architectures to different hardware requirements. The code and appendix can be found at https://github.com/Applied-Machine-Learning-Lab/DANCE.

Modern recommendation systems face significant challenges in processing multimodal sequential data, particularly in temporal dynamics modeling and information flow coordination. Traditional approaches struggle with distribution discrepancies between heterogeneous features and noise interference in multimodal signals. We propose FindRec (Flexible unified information disentanglement for multi-modal sequential Rec ommendation), introducing a novel ''information flow-control-output'' paradigm. The framework features two key innovations: (1) A Stein kernel-based Integrated Information Coordination Module (IICM) that theoretically guarantees distribution consistency between multimodal features and ID streams, and (2) A cross-modal expert routing mechanism that adaptively filters and combines multimodal features based on their contextual relevance. Our approach leverages multi-head subspace decomposition for routing stability and RBF-Stein gradient for unbiased distribution alignment, enhanced by linear-complexity Mamba layers for efficient temporal modeling. Extensive experiments on three real-world datasets demonstrate FindRec's superior performance over state-of-the-art baselines, particularly in handling long sequences and noisy multimodal inputs. Our framework achieves both improved recommendation accuracy and enhanced model interpretability through its modular design. The implementation code is available anonymously online for easy reproducibility https://github.com/Applied-Machine-Learning-Lab/FindRec.

Recent advances in generative models have highlighted the need for robust detectors capable of distinguishing real images from AI-generated images. While existing methods perform well on known generators, their performance often declines when tested with newly emerging or unseen generative models due to overlapping feature embeddings that hinder accurate cross-generator classification. In this paper, we propose Multimodal Discriminative Representation Learning for Generalizable AI-generated Image Detection (MiraGe), a method designed to learn generator-invariant features. Motivated by theoretical insights on intra-class variation minimization and inter-class separation, MiraGe tightly aligns features within the same class while maximizing separation between classes, enhancing feature discriminability. Moreover, we apply multimodal prompt learning to further refine these principles into CLIP, leveraging text embeddings as semantic anchors for effective discriminative representation learning, thereby improving generalizability. Comprehensive experiments across multiple benchmarks show that MiraGe achieves state-of-the-art performance, maintaining robustness even against unseen generators like Sora.

We study the machine unlearning problem which aims to remove specific training data from a pre-trained machine learning model to allow users to exercise their 'right to be forgotten' to protect user privacy. Conventional machine unlearning methods would degrade the model performance after the unlearning procedure. To mitigate the issue, they typically rely on the access to the remaining training data to fine-tune the unlearned model to mitigate the influence of unlearning. However, accessing the remaining training data may not always be practical for different reasons (e.g., data expiration policies, storage limitations, or additional privacy constraints). Machine unlearning without access to the remaining training data poses significant challenges to retaining model performance. In this paper, we study how to unlearn specific training data from a pre-trained model without accessing the remaining training data and protect model performance without dramatically changing the model's parameters. We propose a practical method called Targeted Label Noise Injection. Intuitively, our method assigns incorrect yet controllable labels to the examples that need to be forgotten and fine-tunes the pre-trained model to learn these new labels. This strategy effectively moves the to-be-forgotten examples across the decision boundary with a small impact on the model's overall performance. We theoretically prove the effectiveness of the proposed method and empirically show that it achieves state-of-the-art unlearning performance across various datasets.

Abstract Detecting out-of-distribution (OOD) inputs plays a crucial role in guaranteeing the reliability of deep neural networks (DNNs) when deployed in real-world scenarios. However, DNNs typically exhibit overconfidence in OOD samples, which is attributed to the similarity in patterns between OOD and in-distribution (ID) samples. To mitigate this overconfidence, advanced approaches suggest the incorporation of auxiliary OOD samples during model training, where the outliers are assigned with an equal likelihood of belonging to any category. However, identifying outliers that share patterns with ID samples poses a significant challenge. To address the challenge, we propose a novel method, V irtual O utlier S m o othing (VOSo), which constructs auxiliary outliers using ID samples, thereby eliminating the need to search for OOD samples. Specifically, VOSo creates these virtual outliers by perturbing the semantic regions of ID samples and infusing patterns from other ID samples. For instance, a virtual outlier might consist of a cat’s face with a dog’s nose, where the cat’s face serves as the semantic feature for model prediction. Meanwhile, VOSo adjusts the labels of virtual OOD samples based on the extent of semantic region perturbation, aligning with the notion that virtual outliers may contain ID patterns. Extensive experiments are conducted on diverse OOD detection benchmarks, demonstrating the effectiveness of the proposed VOSo. Our code will be available at https://github.com/junz-debug/VOSo .

Feature noise and label noise are ubiquitous in practical scenarios, which pose great challenges for training a robust machine learning model. Most previous approaches usually deal with only a single problem of either feature noise or label noise. However, in real-world applications, hybrid noise, which contains both feature noise and label noise, is very common due to the unreliable data collection and annotation processes. Although some results have been achieved by a few representation learning based attempts, this issue is still far from being addressed with promising performance and guaranteed theoretical analyses. To address the challenge, we propose a novel unified learning framework called Feature and Label Recovery (FLR) to combat the hybrid noise from the perspective of data recovery, where we concurrently reconstruct both the feature matrix and the label matrix of input data. Specifically, the clean feature matrix is discovered by the low-rank approximation, and the ground-truth label matrix is embedded based on the recovered features with a nuclear norm regularization. Meanwhile, the feature noise and label noise are characterized by their respective adaptive matrix norms to satisfy the corresponding maximum likelihood. As this framework leads to a non-convex optimization problem, we develop the non-convex Alternating Direction Method of Multipliers (ADMM) with the convergence guarantee to solve our learning objective. We also provide the theoretical analysis to show that the generalization error of FLR can be upper-bounded in the presence of hybrid noise. Experimental results on several typical benchmark datasets clearly demonstrate the superiority of our proposed method over the state-of-the-art robust learning approaches for various noises.

Recommender systems have become important tools in the daily life of human beings since they are powerful to address information overload, and discover relevant and useful items for users. The success of recommender systems largely relies on the interaction history between users and items, which is expected to accurately reflect the preferences of users on items. However, the expectation is easily broken in practice, due to the corruptions made in the interaction history, resulting in unreliable and untrusted recommender systems. Previous works either ignore this issue (assume that the interaction history is precise) or are limited to handling additive noise. Motivated by this, in this paper, we study rating flip noise which widely exists in the interaction history of recommender systems and combat it by modelling the noise generation process. Specifically, the rating flip noise allows a rating to be flipped to any other ratings within the given rating set, which reflects various real-world situations of rating corruption, e.g., a user may randomly click a rating from the rating set and then submit it. The noise generation process is modelled by the noise transition matrix that denotes the probabilities of a clean rating flip into a noisy rating. A statistically consistent algorithm is afterwards applied with the estimated transition matrix to learn a robust recommender system against rating flip noise. Comprehensive experiments on multiple benchmarks confirm the superiority of our method.