Scaling laws have enabled large language models(LLMs) to achieve remarkable performance and strong generalization across diverse language understanding tasks, including few-shot, in-context, and zero-shot learning. While prior studies in large-scale collaborative filtering(CF) have revealed clear relationships between model performance and scaling factors such as data size and model capacity, little attention has been given to how heterogeneous datasets can be synergistically combined for recommender systems(RS). In particular, it remains unclear whether systematically integrating diverse recommendation datasets can yield scaling behaviors analogous to those observed in LLMs, while simultaneously addressing challenges such as cold-start recommendation and cross-domain transfer. In this paper, we present RecCLIP, a multimodal framework that reformulates user--item interactions as visual representations compatible with vision--language models(VLMs). RecCLIP compresses interaction signals and employs prompt-based ranking to enable unified representation across heterogeneous data sources. Extensive experiments reveal consistent power-law scaling trends with respect to data size, and demonstrate that RecCLIP achieves superior performance in both cold-start and cross-domain transfer scenarios. Our findings underscore the importance of data-centric design in recommender systems and provide practical insights into scaling them effectively.The code for replication is available at https://github.com/jinliwei-1/RecCLIP.

Generative retrieval presents a promising approach to information retrieval, streamlining both indexing and retrieval processes through end-to-end optimization. This method typically involves assigning a unique identifier to each document, with the retrieval goal being the generation of the correct document identifier in response to a query. Although generative retrieval has demonstrated empirical success in various tasks, designing an effective document identifier remains a challenge. Previous studies have either depended excessively on one-to-one discrete identifiers, leading to increased retrieval latency and loss of semantics in documents or have used retrieval-agnostic dense document identifiers, which can hinder performance. To this end, we propose to integrate the benefits of generative retrieval and dense retrieval using an encoder-decoder-based pre-trained language model. Particularly, the decoder, i.e., the discrete identifier, functions as a coarse retriever, effectively reducing the retrieval space in an end-to-end manner. As a complement, the encoder, i.e., the dense vector, serves as a fine-grained retriever, efficiently and precisely ranking documents in a condensed space. Accordingly, we introduce a three-stage end-to-end learning framework that optimizes identifiers and vectors. Extensive experiments reveal that the proposed method exceeds the current models in terms of effectiveness and time efficiency, across both small and larger corpus sets.

This is an erratum for the article “Learning Discrete Identifiers and Dense Vectors for Generative Retrieval” published in ACM Trans. Inf. Syst. 44, 2, Article 42 (December 2025), 24 pages.

The geographic location of social media users is crucial for understanding user behavior, optimizing advertising, and supporting location-based services such as emergency awareness and event monitoring services. However, existing Twitter user geolocation methods primarily focus on explicit social relationships between users while overlooking implicit location correlations, which affects the accuracy of user geolocation. To address this, this article proposes a Twitter user geolocation method (GeoICMF) based on implicit location correlations and multi-scale feature fusion. GeoICMF introduces a novel location association graph construction method to effectively capture implicit location correlations among users, an innovative multi-scale feature fusion model to dynamically fuse multi-scale features and generate richer user representations, and a pioneering geographic partitioning method to better adapt to user location distributions and enhance geolocation accuracy. Extensive experiments on three real-world datasets demonstrate that GeoICMF outperforms state-of-the-art baseline methods in Twitter user geolocation tasks, validating the effectiveness and superiority of the proposed method.

The geolocation of social users is crucial for understanding user behavior, optimizing advertisement placement, and enhancing public safety.However, existing methods tend to show some deficiencies when handling sparse datasets and may not fully capture the natural clustering characteristics of user locations, thereby resulting in inadequate geolocation accuracy.This paper proposes a novel social user geolocation method (MILGCN) that innovatively integrates Mean Shift Clustering, Incremental Learning, and Graph Convolutional Networks.Specifically, Mean Shift performs fine-grained clustering of user locations based on density peak characteristics, ensuring that geographically close users are grouped into the same cluster.Introducing an incremental learning mechanism into graph convolutional networks enables MILGCN to have progressive learning ability.As a result, the problem of incomplete feature extraction from sparse data is alleviated, resulting in more comprehensive user features and improved geolocation accuracy.Extensive experiments proved that the proposed method significantly outperforms the state-of-the-art baselines on the real Twitter datasets, demonstrating a substantial improvement in geolocation performance.

Image‐to‐image ( I2I ) translation has emerged as a valuable tool for privacy protection in the digital age, offering effective ways to safeguard portrait rights in cyberspace. In addition, I2I translation is applied in real‐world tasks such as image synthesis, super‐resolution, virtual fitting, and virtual live streaming. Traditional I2I translation models demonstrate strong performance when handling similar datasets. However, when the domain distance between two datasets is large, translation quality may degrade significantly due to notable differences in image shape and edges. To address this issue, we propose Long‐Domain Search GAN ( LDSGAN ), an unsupervised I2I translation network that employs a GAN structure as its backbone, incorporating a novel Real‐Time Routing Search ( RTRS ) module and Sketch Loss. Specifically, RTRS aids in expanding the search space within the target domain, aligning feature projection with images closest to the optimization target. Additionally, Sketch Loss retains human visual similarity during long‐domain distance translation. Experimental results indicate that LDSGAN surpasses existing I2I translation models in both image quality and semantic similarity between input and generated images, as reflected by its mean FID and LPIPS scores of 31.509 and 0.581, respectively.

Steganography is a critical information‐hiding technique widely used for the covert transmission of secret information on social media. In contrast, steganalysis plays a key role in ensuring information security. Although various effective steganalysis algorithms have been proposed, existing studies typically treat color images as three independent channels and do not fully consider robust features suitable for JPEG images. To address this limitation, we propose a robust steganalysis algorithm based on high‐dimensional mapping. By analyzing the changes in color images during the JPEG compression and decompression processes, we observe that the embedding of secret information causes shifts in the JPEG coefficients, which subsequently affects feature representation during decompression. Based on this observation, our method captures steganographic traces by utilizing the transformation errors produced during decompression. Additionally, due to the imbalance between luminance and chrominance, the feature weights of each channel are uneven. To ensure balanced analysis across the three channels, we adjust the distribution differences of each channel through high‐dimensional mapping, thereby reducing intraclass feature variations. Experimental results demonstrate that the proposed method outperforms existing approaches in most cases.

Recently, the paradigm of pre-training and fine-tuning has achieved impressive performance owing to their ability to transfer general knowledge from pre-trained domain to target domain. Meanwhile, graph neural networks (GNNs) have gained prominence in recommender systems. However, there is a lack of unified pre-training and fine-tuning paradigms in graph-based recommendation systems. Applying pre-training and fine-tuning in graph-based recommendation is challenging due to the unique characteristics of recommendation data, including the non-uniform representation, negative transfer effects, and skewed data distributions. To overcome these challenges, we introduce pre-training and prompting recommendation ( ProRec ) , a novel model that synergizes uniform graph pre-training with prompt-tuning for recommendation systems. Specifically, to address the challenge of inconsistent features across different recommendation datasets, ProRec constructs unified input features at the subgraph level and uses a graph auto-encoder for pre-training, laying the foundation for uniform knowledge transfer from the pre-trained domain to the downstream domain. Additionally, ProRec employs prompt-tuning during the fine-tuning phase, which, in a parameter-efficient manner, enhances the generalization of pre-trained knowledge to downstream tasks thereby reducing negative transfer effects. Furthermore, a cross-layer contrastive learning strategy is adopted to eliminate uneven data distribution, promoting more evenly distributed and informative representations. Finally, extensive benchmark comparisons have demonstrated that ProRec outperforms the latest state-of-the-art methods. The source code necessary for replication is available at https://github.com/Code2Q/ProRec .

User location discovery from social media is crucial for location-based services such as emergency awareness and event monitoring. Existing approaches generally integrate user-generated text features and social relationships but insufficiently explore location-specific features and geographically proximate relationships, leading to suboptimal accuracy. In this article, we propose a Twitter user geolocation method based on location feature enhancement to better capture the location characteristics in users’ tweets and social relationships. Specifically, a user tweet representation algorithm based on location feature separation (TwLS) is designed. By leveraging words’ location-aware weight matrix and pre-trained embeddings, TwLS calculates a tweet representation for each user in every location, explicitly indicating the relevance between users and various locations. Additionally, we develop the local celebrity discovery method (LocCel) to construct social networks by identifying and preserving geographically concentrated high-degree nodes while filtering noise. Thereby, LocCel enhances local relationships and strengthens location-proximate connections within the user social network. Experiments on two real-world datasets show that our method outperforms seven baselines, improving user geolocation accuracy by 3.1% ∼ 8.1% and 1.8% ∼ 8.8%, while reducing median error by 22.2% ∼ 52.8% and 19.4% ∼ 50.7%, respectively.

Network entities have important asset mapping, vulnerability, and service delivery applications. In cyberspace, where the network structure is complex and the number of entities is large, effectively obtaining the relevant attributes of entities is a difficult task. Graph neural network-based approaches focus on target IP node messaging from neighboring nodes; however, the graph learning task ignores the heterophilous relationship of network entity identification (NEI) tasks in the graph structure and fails to effectively message from non-neighboring nodes. To address the limitations of the existing task, we propose a NEI model based on heterophilous graph learning (HpGraphNEI); HpGraphNEI converts heterophilous graphs under the NEI task into homophilous graphs and uses the graph learning mechanism to carry out attribute completion task for incomplete entity attributes. First, the acquired dataset is feature-extracted by network measurement, and the clustering algorithm is employed to divide the target nodes into communities. Second, the network topology graph is constructed to embed the node attribute information and neighborhood structure information into the graph in the form of feature vectors. Then, the global attention in the community is calculated according to the attention results, the edges with strong correlation in the network are filtered, the adjacency matrix is reconstructed, and then the updated node information is aggregated to complete the incomplete attribute completion. Fourth, the updated nodes are categorized to output network entity categories and construct network entity portraits based on the attribute completion nodes. We conducted a 2-month data collection in three real regions and successfully identified 6 types of network entities. Compared with the optimal baseline, all the metrics have significantly improved, with NEI accuracy above 93.74% and up to 96.28%, improved 2.27% to 2.69%.

The rapid development of DeepFake technologies has brought great challenges to the authenticity of video contents. It is of vital importance to develop DeepFake detection methods, among which three-dimensional (3D) convolution neural networks (CNN) have attracted wide interest and achieved satisfying performances. However, there are few 3D CNNs designed for DeepFake detection and the parameters of them are large, which cause heavy memory and storage consumption. In this paper, a lightweight 3D CNN is proposed for DeepFake detection. Channel transformation module is designed to extract features with much fewer parameters in higher level. Serving as spatial-temporal module, 3D CNNs are adopted to fuse the spatial features in time dimension. To suppress frame content and highlight frame texture, spatial rich model features are extracted from the input frames, which helps the spatial-temporal module achieve better performance. Experimental results show that the number of parameters of the proposed network is much less than those of other networks and the proposed network outperforms other state-of-the-art DeepFake detection methods on mainstream DeepFake data sets.

Social network user location inference technology has been widely used in various geospatial applications like public health monitoring and local advertising recommendation. Due to insufficient consideration of relationships between users and location indicative words, most of existing inference methods estimate label propagation probabilities solely based on statistical features, resulting in large location inference error. In this paper, a Twitter user location inference method based on representation learning and label propagation is proposed. Firstly, the heterogeneous connection relation graph is constructed based on relationships between Twitter users and relationships between users and location indicative words, and relationships unrelated to geographic attributes are filtered. Then, vector representations of users are learnt from the connection relation graph. Finally, label propagation probabilities between adjacent users are calculated based on vector representations, and the locations of unknown users are predicted through iterative label propagation. Experiments on two representative Twitter datasets - GeoText and TwUs, show that the proposed method can accurately calculate label propagation probabilities based on vector representations and improve the accuracy of location inference. Compared with existing typical Twitter user location inference methods - GCN and MLP-TXT+NET, the median error distance of the proposed method is reduced by 18% and 16%, respectively.

In recent years, with the prevalence of social media and smart devices, people causally reveal their locations such as shops, hotels, and restaurants in their tweets. Recognizing and linking such fine-grained location mentions to well-defined location profiles are beneficial for retrieval and recommendation systems. In this paper, we propose DLocRL, a new deep learning pipeline for fine-grained location recognition and linking in tweets, and verify its effectiveness on a real-world Twitter dataset.

Both reviews and user-item interactions (i.e., rating scores) have been widely adopted for user rating prediction. However, these existing techniques mainly extract the latent representations for users and items in an independent and static manner. That is, a single static feature vector is derived to encode user preference without considering the particular characteristics of each candidate item. We argue that this static encoding scheme is incapable of fully capturing users’ preferences, because users usually exhibit different preferences when interacting with different items. In this article, we propose a novel c ontext- a ware user-item r epresentation l earning model for rating prediction, named CARL. CARL derives a joint representation for a given user-item pair based on their individual latent features and latent feature interactions. Then, CARL adopts Factorization Machines to further model higher order feature interactions on the basis of the user-item pair for rating prediction. Specifically, two separate learning components are devised in CARL to exploit review data and interaction data, respectively: review-based feature learning and interaction-based feature learning . In the review-based learning component, with convolution operations and attention mechanism, the pair-based relevant features for the given user-item pair are extracted by jointly considering their corresponding reviews. However, these features are only reivew-driven and may not be comprehensive. Hence, an interaction-based learning component further extracts complementary features from interaction data alone, also on the basis of user-item pairs. The final rating score is then derived with a dynamic linear fusion mechanism. Experiments on seven real-world datasets show that CARL achieves significantly better rating prediction accuracy than existing state-of-the-art alternatives. Also, with the attention mechanism, we show that the pair-based relevant information (i.e., context-aware information) in reviews can be highlighted to interpret the rating prediction for different user-item pairs.

With the dimension of steganalysis feature increases rapidly, ensemble steganalysis has become the trend, and its performance is greatly influenced by the selection of feature subspaces. In order to select feature subspaces more effectively to improve the performance of ensemble steganalysis, a feature subspace selection algorithm based on Fisher criterion is proposed. The proposed selection algorithm computes weight for each feature component according to its Fisher criterion value and a base probability value, then selects the feature components with the probabilities in proportion to their weights. When it is used to improve the ensemble steganalysis, the appropriate base probability value is searched by steps. Experimental results show that for J-UNIWARD (JPEG UNIversal WAvelet Relative Distortion) steganography, the proposed feature subspace selection algorithm can select more effective feature subspaces, and enhance the detection performance of GFR (Gabor Filter Residual) feature.