Comparative Study of Adversarial Training Methods for Cold-Start Recommendation

Ma, Haokai; Li, Xiangxian; Meng, Lei; Meng, Xiangxu

doi:10.1145/3475724.3483600

Cited by 12 publications

(2 citation statements)

References 25 publications

(78 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Personalized recommendation aims to capture user preference from the massive user behaviors and predict the appropriate items the user will be interested in (Meng et al 2020;Ma et al 2021Ma et al , 2023a. Sequential recommendation (SR) is a effective method for inferring dynamic interests from the user's historical behavior sequences (Zhang et al 2022;Chen et al 2022).…”

Section: Introductionmentioning

confidence: 99%

Plug-In Diffusion Model for Sequential Recommendation

Ma,

Xie,

Meng

et al. 2024

AAAI

View full text Add to dashboard Cite

Pioneering efforts have verified the effectiveness of the diffusion models in exploring the informative uncertainty for recommendation. Considering the difference between recommendation and image synthesis tasks, existing methods have undertaken tailored refinements to the diffusion and reverse process. However, these approaches typically use the highest-score item in corpus for user interest prediction, leading to the ignorance of the user's generalized preference contained within other items, thereby remaining constrained by the data sparsity issue. To address this issue, this paper presents a novel Plug-in Diffusion Model for Recommendation (PDRec) framework, which employs the diffusion model as a flexible plugin to jointly take full advantage of the diffusion-generating user preferences on all items. Specifically, PDRec first infers the users' dynamic preferences on all items via a time-interval diffusion model and proposes a Historical Behavior Reweighting (HBR) mechanism to identify the high-quality behaviors and suppress noisy behaviors. In addition to the observed items, PDRec proposes a Diffusion-based Positive Augmentation (DPA) strategy to leverage the top-ranked unobserved items as the potential positive samples, bringing in informative and diverse soft signals to alleviate data sparsity. To alleviate the false negative sampling issue, PDRec employs Noise-free Negative Sampling (NNS) to select stable negative samples for ensuring effective model optimization. Extensive experiments and analyses on four datasets have verified the superiority of the proposed PDRec over the state-of-the-art baselines and showcased the universality of PDRec as a flexible plugin for commonly-used sequential encoders in different recommendation scenarios. The code is available in https://github.com/hulkima/PDRec.

show abstract

Section: Introductionmentioning

confidence: 99%

Plug-In Diffusion Model for Sequential Recommendation

Ma,

Xie,

Meng

et al. 2024

AAAI

View full text Add to dashboard Cite

show abstract

“…Due to the popularity of multi-modal data [12], images are usually accompanied by semantic information such as tags or description words, which make it easier for the classification model to distinguish confusing classes, as shown in Fig. 1.…”

Section: Introductionmentioning

confidence: 99%

Cross-modal learning using privileged information for long-tailed image classification

Li,

Zheng,

et al. 2024

Comp. Visual Media

View full text Add to dashboard Cite

The prevalence of long-tailed distributions in real-world data often results in classification models favoring the dominant classes, neglecting the less frequent ones. Current approaches address the issues in long-tailed image classification by rebalancing data, optimizing weights, and augmenting information. However, these methods often struggle to balance the performance between dominant and minority classes because of inadequate representation learning of the latter. To address these problems, we introduce descriptional words into images as cross-modal privileged information and propose a cross-modal enhanced method for long-tailed image classification, referred to as CMLTNet. CMLTNet improves the learning of intraclass similarity of tail-class representations by cross-modal alignment and captures the difference between the head and tail classes in semantic space by cross-modal inference. After fusing the above information, CMLTNet achieved an overall performance that was better than those of benchmark long-tailed and cross-modal learning methods on the long-tailed cross-modal datasets, NUS-WIDE and VireoFood-172. The effectiveness of the proposed modules was further studied through ablation experiments. In a case study of feature distribution, the proposed model was better in learning representations of tail classes, and in the experiments on model attention, CMLTNet has the potential to help learn some rare concepts in the tail class through mapping to the semantic space.

show abstract

Unsupervised Segmentation of Haze Regions as Hard Attention for Haze Classification

Li,

Ma,

et al. 2023

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Comparative Study of Adversarial Training Methods for Cold-Start Recommendation

Cited by 12 publications

References 25 publications

Plug-In Diffusion Model for Sequential Recommendation

Plug-In Diffusion Model for Sequential Recommendation

Cross-modal learning using privileged information for long-tailed image classification

Unsupervised Segmentation of Haze Regions as Hard Attention for Haze Classification

Contact Info

Product

Resources

About