Cold-start remains a fundamental challenge in recommendation systems due to the scarcity of interaction data. Recent methods address this issue by leveraging semantic ID embeddings and cross-domain transfer techniques, achieving notable progress. However, the common practice of learning semantic ID embeddings and training the recommendation model in separate stages hinders the generalization capability of semantic IDs throughout the training process. In this work, we propose Sharpness-Consistent Cross-Domain Recommendation (SC2 Rec), a novel framework designed to enhance the generalization of semantic ID-based models in cold-start scenarios. SC2 Rec alternately optimizes the sharpness of the loss landscape and enforces landscape consistency between warm and cold domains, leading to unified and flatter minima and improved generalization. Extensive experiments on industrial datasets demonstrate the effectiveness of SC2 Rec. Furthermore, we release a high-quality dataset to facilitate further research in this area.

Multi-behavior recommender systems have demonstrated their effectiveness in mitigating issues such as data sparsity by incorporating auxiliary behaviors into the target behavior. However, existing multi-behavior recommendation approaches typically take one of two directions: (1) fusing behavior-specific preference features from various behavior interaction graphs explicitly or implicitly for recommendation; or (2) utilizing behavior-unified preference features from the unified interaction graph for recommendation or to initialize features for subsequent modeling. These methods fail to exploit the integration of behavior-unified global and behavior-specific local preference features, resulting in incomplete preference modeling. To address this issue, in this work, we propose a novel method calledUnifyingGlobal andLocalPreferences (UGLP) for multi-behavior recommendation. In UGLP, we design a behavior feature fusion network that consists of global and local fusion modules for comprehensive and fine-grained user preferences. The global fusion module performs graph convolution on behavior-unified global and behavior-specific local interaction graphs to obtain behavior-unified and behavior-specific features. The behavior-unified and behavior-specific features are then fused into globally fused features via a gating network. The local fusion module then performs cross-behavior fusion on these globally fused features via another gating network. We introduce a contrastive learning module to promote preference alignment and knowledge transfer from auxiliary behaviors to the target behavior. Additionally, we incorporate a GCN refinement module to adjust the fused features to ensure that both global and local user preferences are learned. Experimental results on three real-world datasets verify that our method is able to surpass various state-of-the-art models. For instance, our method outperforms the best baseline by an average of 16.43% and 14.36% in terms of HR@10 and NDCG@10, respectively.

In recommender systems, accurate post-click conversion rate (CVR) estimation is crucial for a company’s revenue growth. Currently, multi-task causal methods—such as multi-task doubly robust learning—improve CVR estimation by reducing bias and variance during training. However, these methods often overlook the impact of hard-to-classify samples, which deviate significantly from the sample cluster center and substantially increase the bias and variance of multi-task causal approaches. To address this limitation, we propose a novel inverse contrastive representation learning guided causal multi-task framework. Specifically, we first select clicked and unclicked samples that deviate significantly from their respective cluster centers to form negative pairs. We then apply inverse contrastive representation learning (ICRL) to pull these negative pairs closer together, encouraging deviated clicked samples to move closer to the clicked cluster center, and vice versa. This approach yields a more accurate and lower-variance inverse propensity score for the CVR estimator. Additionally, we compute the ICRL loss segmentally to reduce computational resource consumption. We conduct extensive experiments on six large-scale datasets, as well as online A/B tests on our advertising platform. Our method achieves a 2.9% improvement on offline datasets compared to state-of-the-art baselines, and a 0.6% increase over the online production model.

Image-text retrieval (ITR) has been one of the primary tasks in cross-modal retrieval, serving as a crucial bridge between computer vision and natural language processing. Significant progress has been made to achieve global alignment and local alignment between images and texts by mapping images and texts into a common space to establish correspondences between these two modalities. However, the rich semantic content contained in each image may bring false matches, resulting in the matched text ignoring the main semantics but focusing on the secondary or other semantics of this image. To address this issue, this paper proposes a semantically optimized approach with a novel Main Semantics Consistency (MSC) loss function, which aims to rank the semantically most similar images (or texts) corresponding to the given query at the top position during the retrieval process. First, in each batch of image-text pairs, we separately compute (i) the image-image similarity, i.e., the similarity between every two images, (ii) the text-text similarity, i.e., the similarity between a group of texts (that belong to a certain image) and another group of texts (that belong to another image), and (iii) the image-text similarity, i.e., the similarity between each image and each text. Afterward, our proposed MSC effectively aligns the above image-image, image-text, and text-text similarity, since the main semantics of every two images will be highly close if their text descriptions remain highly semantically consistent. By this means, we can capture the main semantics of each image to be matched with its corresponding texts, prioritizing the semantically most related retrieval results. Extensive experiments on MSCOCO and FLICKR30K verify the superior performance of MSC compared with the SOTA image-text retrieval methods. The source code of this project is released at GitHub: https://github.com/xyi007/MSC.

In online advertising, the sample selection bias problem is a major cause of inaccurate conversion rate estimates. Current mainstream solutions only perform causality-based optimization in the click space since the conversion labels in the non-click space are absent. However, optimization for unclicked samples is equally essential because the non-click space contains more samples and user characteristics than the click space. To exploit the unclicked samples, we propose a Direct Dual Propensity Optimization (DDPO) framework to optimize the model directly in impression space with both clicked and unclicked samples. In this framework, we specifically design a click propensity network and a conversion propensity network. The click propensity network is dedicated to ensuring that optimization in the click space is unbiased. The conversion propensity network is designed to generate pseudo-conversion labels for unclicked samples, thus overcoming the challenge of absent labels in non-click space. With these two propensity networks, we are able to perform causality-based optimization in both click space and non-click space. In addition, to strengthen the causal relationship, we design two causal transfer modules for the conversion rate prediction model with the attention mechanism. The proposed framework is evaluated on five real-world public datasets and one private Tencent advertising dataset. Experimental results verify that our method is able to improve the prediction performance significantly. For instance, our method outperforms the previous state-of-the-art method by 7.0% in terms of the Area Under the Curve on the Ali-CCP dataset.

In real-world industrial scenarios, post-click conversion rate (CVR) prediction models are trained offline based on click events and subsequently applied online to both clicked and unclicked events. Unfortunately, unclicked events are inevitably difficult to estimate due to user self-selection, which leads to a degradation of CVR prediction accuracy. In order to estimate the prediction of unclicked events, the current mainstream Doubly Robust (DR) estimators introduce the concept of imputed errors. However, inaccuracies in imputed errors can increase the uncertainty in the generalization bound of CVR predictions, consequently resulting in a decline in the CVR prediction accuracy. To challenge this issue, we first present a theoretical analysis of the bias and variance inherent in DR estimators and then introduce a novel causal estimator that seeks to strike a balance between bias and variance within the DR framework, thus optimizing the learning of the imputation model in a more robust manner. Additionally, drawing inspiration from adversarial learning techniques, we propose a novel dual adversarial component, which learns from both the space level and the task level to eliminate the causal influence of input features on the CTR task (i.e., the click propensity), with the goal of achieving unbiased estimations. Our extensive experimental evaluations, conducted on both the widely used benchmark and the real-world large-scale Internet giant platform, convincingly demonstrate the effectiveness of our proposed scheme. Besides, we have released a high-quality industrial dataset named Tenc-UnionAds used for selection bias research in the advertising field.

Hashing-based recommender systems that represent users and items as binary hash codes are recently proposed to significantly improve time and space efficiency. However, the highly developed social media presents two major challenges to hashing-based recommendation algorithms. Firstly, the boundary between information producers and consumers becomes blurred, resulting in the rapid emergence of massive online content. Meanwhile, users' limited information consumption capacity inevitably causes further interaction sparsity. The inherent high sparsity of data leads to insufficient hash learning. Secondly, a considerable amount of online content becomes fast-moving consumer goods, such as short videos and news commentary, causing frequent changes in user interests and item popularity. To address the above problems, we propose a Temporal Social Graph Network Hashing (TSGNH) method for efficient recommendation, which generates binary hash codes of users and items through dynamic-adaptive aggregation on a constructed temporal social graph network. Specifically, we build a temporal social graph network to fully capture the social information widely existing in practical recommendation scenarios and propose a dynamic-adaptive aggregation method to capture long-term and short-term characters of users and items. Furthermore, different from the discrete optimization approaches used by existing hashing-based recommendation methods, we devise an end-to-end hashing learning approach that incorporates balanced and de-correlated constraints to learn compact and informative binary hash codes tailored for recommendation scenarios. Extensive experiments on three widely evaluated recommendation datasets demonstrate the superiority of the proposed method.

With the explosive growth of multimedia contents, multimedia retrieval is facing unprecedented challenges on both storage cost and retrieval speed. Hashing technique can project the high-dimensional data into compact binary hash codes. With it, the most time-consuming semantic similarity computation during the multimedia retrieval process can be significantly accelerated with fast Hamming distance computation, and meanwhile the storage cost can be reduced greatly by the binary embedding. In the light of this, multi-modal hashing has recently received considerable attention to support large-scale multimedia retrieval. Different from uni-modal hashing, the multi-modal hashing focuses on modeling the multi-modal semantics and further preserving them into binary hash codes with hash learning. In this paper, we first systematically review the existing learning to hash methods for efficient multimedia retrieval, categorizing them according to the multimedia retrieval tasks, the specific multi-modal semantic modeling techniques, and hash learning strategies. Thereafter, we present the performance comparison results. We ultimately discuss the challenges and potential research directions that may require further investigation in multi-modal hash learning.

Data scarcity is a perpetual challenge of recommendation systems, and researchers have proposed a variety of cross-domain recommendation methods to alleviate the problem of data scarcity in target domains. However, in many real-world cross-domain recommendation systems, the source domain and the target domain are sampled from different data distributions, which obstructs the cross-domain knowledge transfer. In this article, we propose to specifically align the data distributions between the source domain and the target domain to alleviate imbalanced sample distribution and thus challenge the data scarcity issue in the target domain. Technically, our proposed approach builds a dual adversarial adaptation (DAA) framework to adversarially train the target model together with a pre-trained source model. Two domain discriminators play the two-player minmax game with the target model and guide the target model to learn reliable domain-invariant features that can be transferred across domains. At the same time, the target model is calibrated to learn domain-specific information of the target domain. In addition, we formulate our approach as a plug-and-play module to boost existing recommendation systems. We apply the proposed method to address the issues of insufficient data and imbalanced sample distribution in real-world Click-through Rate/Conversion Rate predictions on two large-scale industrial datasets. We evaluate the proposed method in scenarios with and without overlapping users/items, and extensive experiments verify that the proposed method is able to significantly improve the prediction performance on the target domain. For instance, our method can boost PLE with a performance improvement of 15.4% in terms of Area Under Curve compared with single-domain PLE on our private game dataset. In addition, our method is able to surpass single-domain MMoE by 6.85% on the public datasets. Code: https://github.com/TL-UESTC/DAA .

Deep cross-modal hashing has promoted the field of multi-modal retrieval due to its excellent efficiency and storage, but its vulnerability to backdoor attacks is rarely studied. Notably, current deep cross-modal hashing methods inevitably require large-scale training data, resulting in poisoned samples with imperceptible triggers that can easily be camouflaged into the training data to bury backdoors in the victim model. Nevertheless, existing backdoor attacks focus on the uni-modal vision domain, while the multi-modal gap and hash quantization weaken their attack performance. In addressing the aforementioned challenges, we undertake an invisible black-box backdoor attack against deep cross-modal hashing retrieval in this article. To the best of our knowledge, this is the first attempt in this research field. Specifically, we develop a flexible trigger generator to generate the attacker’s specified triggers, which learns the sample semantics of the non-poisoned modality to bridge the cross-modal attack gap. Then, we devise an input-aware injection network, which embeds the generated triggers into benign samples in the form of sample-specific stealth and realizes cross-modal semantic interaction between triggers and poisoned samples. Owing to the knowledge-agnostic of victim models, we enable any cross-modal hashing knockoff to facilitate the black-box backdoor attack and alleviate the attack weakening of hash quantization. Moreover, we propose a confusing perturbation and mask strategy to induce the high-performance victim models to focus on imperceptible triggers in poisoned samples. Extensive experiments on benchmark datasets demonstrate that our method has a state-of-the-art attack performance against deep cross-modal hashing retrieval. Besides, we investigate the influences of transferable attacks, few-shot poisoning, multi-modal poisoning, perceptibility, and potential defenses on backdoor attacks. Our codes and datasets are available at https://github.com/tswang0116/IB3A.

Unsupervised multi-view feature selection aims to select informative features with multi-view features and unsupervised learning. It is a challenging problem due to the absence of explicit semantic supervision. Recently, graph theory and hard pseudo-label learning have been adopted to solve multi-view feature selection problems under the unsupervised learning paradigm. However, graph-based methods are difficult to support large-scale real scenarios due to the high computational complexity of graph construction. Moreover, existing methods based on hard pseudo-label learning generally result in significant information loss. In this article, we propose an Adaptive Collaborative Soft Label Learning (ACSLL) model for unsupervised multi-view feature selection. In this model, collaborative soft label learning and multi-view feature selection are integrated into a unified framework. Specifically, we learn the pseudo soft labels from each view feature by a simple and efficient method and fuse them with an adaptive weighting strategy into a joint soft label matrix. This matrix is further used for guiding the feature selection process to identify valuable features. An effective optimization strategy guaranteed with proven convergence is derived to iteratively solve this problem. Experiments demonstrate the superiority of the proposed method in both feature selection accuracy and efficiency.

Semi-supervised feature selection methods jointly exploit the labelled and unlabeled samples when selecting the features. Under the semi-supervised learning scenario, the number of labelled data significantly impacts the feature selection performance. In this paper, we introduce the label learning with binary hashing to the research field of feature selection and propose a novel Semi-supervised Feature Selection with Binary Label Learning (SFS-BLL) model. Specifically, we learn the binary hash codes as the pseudo labels by specially imposing binary hash constraints on the spectral embedding process to increase the number of labels. Meanwhile, we propose a self-weighted sparse regression module which exploits the learned labels and given manual labels together with importance differentiation to guide the feature selection process. Finally, we develop an effective discrete optimization method based on the Alternating Direction Method of Multipliers (ADMM) to iteratively optimize the binary labels and the feature selection matrix. Extensive experiments on widely tested benchmarks demonstrate the superiority of the proposed method from various aspects.

Hashing is an effective technique to improve the efficiency of large-scale recommender system by representing both users and items into binary codes. However, existing hashing-based recommendation methods still suffer from two important problems: 1) Cold-start. They employ the user-item interactions and single auxiliary information to learn the binary hash codes. But the full interaction history is not always available and the single auxiliary information may be missing. 2) Efficient optimization. They learn the hash codes with two-step relaxed optimization or one-step discrete hash optimization based on the cyclic coordinate descent, which results in significant quantization loss or still consumes considerable computation time. In this paper, we propose a Multi-modal Discrete Collaborative Filtering (MDCF) for efficient cold-start recommendation. We map the multi-modal features of users and items to a consensus Hamming space based on the matrix factorization framework. Specifically, a low-rank self-weighted multi-modal fusion module is designed to adaptively fuse the multi-modal features into binary hash codes. Additionally, to support large-scale recommendation, a fast discrete optimization method based on augmented Lagrangian multiplier is developed to directly compute the binary hash codes with simple operations. Experiments show the superior performance of the proposed method over state-of-the-art baselines.

Unsupervised cross-modal hashing has attracted considerable attention to support large-scale cross-modal retrieval. Although promising progresses have been made so far, existing methods still suffer from limited capability on excavating and preserving the intrinsic multi-modal semantics. In this paper, we propose a Correlation-Identity Reconstruction Hashing (CIRH) method to alleviate this challenging problem. We develop a new unsupervised deep cross-modal hash learning framework to model and preserve the heterogeneous multi-modal correlation semantics into both hash codes and functions, and simultaneously, we involve both the hash codes and functions with the descriptive identity semantics. Specifically, we construct a multi-modal collaborated graph to model the heterogeneous multi-modal correlations, and jointly perform the intra-modal and cross-modal semantic aggregation on homogeneous and heterogeneous graph networks to generate a multi-modal complementary representation with correlation reconstruction. Furthermore, an identity semantic reconstruction process is designed to involve the generated representation with identity semantics by reconstructing the input modality representations. Finally, we propose a correlation-identity consistent hash function learning strategy to transfer the modelled multi-modal semantics into the neural networks of modality-specific deep hash functions. Experiments demonstrate the superior performance of the proposed method on both retrieval accuracy and efficiency. We provide our source codes and experimental datasets athttps://github.com/XizeWu/CIRH

Using hashing to learn the binary codes of users and items significantly improves the efficiency and reduces the space consumption of the recommender system. However, existing hashing-based recommender systems remain black boxes without any explainable outputs that illustrate why the system recommends the items. In this paper, we present a new end-to-end discrete recommendation framework based on the multi-task learning to simultaneously perform explainable and efficient recommendation. Toward this goal, an Explainable Discrete Collaborative Filtering (EDCF) method is proposed to preserve the user-item interaction features and semantic text features into binary hash codes by adaptively exploiting the correlations between the preference prediction task and the explanation generation task. At the online recommendation stage, EDCF makes efficient top-K recommendation by calculating the Hamming distances between the feature hash codes, and simultaneously generates natural language explanations for recommendation results through the explanation generation module. To obtain the hash codes directly from the end-to-end neural network, we introduce an attentive TextCNN and an Adaptive Tanh layer in the preference prediction task. For explanation generation, Long Short-Term Memory is employed to generate the explanations for recommendation results from the binary hash codes of user and item. Experiments demonstrate the superiority of the proposed method.

Deep cross-modal hashing retrieval models inherit the vulnerability of deep neural networks. They are vulnerable to adversarial attacks, especially for the form of subtle perturbations to the inputs. Although many adversarial attack methods have been proposed to handle the robustness of hashing retrieval models, they still suffer from two problems: (1) Most of them are based on the white-box settings, which is usually unrealistic in practical application. (2) Iterative optimization for the generation of adversarial examples in them results in heavy computation. To address these problems, we propose an Efficient Query-based Black-Box Attack (EQB 2 A) against deep cross-modal hashing retrieval, which can efficiently generate adversarial examples for the black-box attack. Specifically, by sending a few query requests to the attacked retrieval system, the cross-modal retrieval model stealing is performed based on the neighbor relationship between the retrieved results and the query, thus obtaining the knockoffs to substitute the attacked system. A multi-modal knockoffs-driven adversarial generation is proposed to achieve efficient adversarial example generation. While the entire network training converges, EQB 2 A can efficiently generate adversarial examples by forward-propagation with only given benign images. Experiments show that EQB 2 A achieves superior attacking performance under the black-box setting.

Cross-domain recommendation aims to exploit heterogeneous information from a data-sufficient domain (source domain) to transfer knowledge to a data-scarce domain (target domain). A majority of existing methods focus on unidirectional transfer that leverages the domain-shared information to facilitate the recommendation of the target domain. Nevertheless, it is more beneficial to improve the recommendation performance of both domains simultaneously via a dual transfer learning schema, which is known as bidirectional cross-domain recommendation (BCDR). Existing BCDR methods have their limitations, since they only perform bidirectional transfer learning based on domain-shared representations while neglecting rich information that is private to each domain. In this article, we argue that users may have domain-biased preferences due to the characteristics of that domain. Namely, the domain-specific preference information also plays a critical role in the recommendation. To effectively leverage the domain-specific information, we propose a M ulti-level A ttention-based D omain D isentanglement framework dubbed MADD for BCDR, which explicitly leverages the attention mechanism to construct personalized preference with both domain-invariant and domain-specific features obtained by disentangling raw user embeddings. Specifically, the domain-invariant feature is exploited by domain-adversarial learning while the domain-specific feature is learned by imposing an orthogonal loss. We then conduct a reconstruction process on disentangled features to ensure semantic-sufficiency. After that, we devise a multi-level attention mechanism for these disentangled features, which determines their contributions to the final personalized user preference embedding by dynamically learning the attention scores of individual features. We train the model in a multi-task learning fashion to benefit both domains. Extensive experiments on real-world datasets demonstrate that our model significantly outperforms state-of-the-art cross-domain recommendation approaches.

Data scarcity, e.g., labeled data being either unavailable or too expensive, is a perpetual challenge of recommendation systems. Cross-domain recommendation leverages the label information in the source domain to facilitate the task in the target domain. However, in many real-world cross-domain recommendation systems, the source domain and the target domain are sampled from different data distributions, which obstructs the cross-domain knowledge transfer. In this paper, we propose to specifically align the data distributions between the source domain and the target domain to alleviate imbalanced sample distribution and thus challenge the data scarcity issue in the target domain. Technically, our proposed approach builds an adversarial adaptation (AA) framework to adversarially train the target model together with a pre-trained source model. A domain discriminator plays the two-player minmax game with the target model and guides the target model to learn domain-invariant features that can be transferred across domains. At the same time, the target model is calibrated to learn domain-specific information of the target domain. With such a formulation, the target model not only learns domain-invariant features for knowledge transfer, but also preserves domain-specific information for target recommendation. We apply the proposed method to address the issues of insufficient data and imbalanced sample distribution in real-world Click-Through Rate (CTR)/Conversion Rate (CVR) predictions on a large-scale dataset. Specifically, we formulate our approach as a plug-and-play module to boost existing recommendation systems. Extensive experiments verify that the proposed method is able to significantly improve the prediction performance on the target domain. For instance, our method can boost PLE with a performance improvement of 13.88% in terms of Area Under Curve (AUC) compared with single-domain PLE.

Multi-modal hashing learns binary hash codes with extremely low storage cost and high retrieval speed. It can support efficient multi-modal retrieval well. However, most existing methods still suffer from three important problems: 1) Limited semantic representation capability with shallow learning. 2) Mandatory feature-level multi-modal fusion ignores heterogeneous multi-modal semantic gaps. 3) Direct coarse pairwise semantic preserving cannot effectively capture the fine-grained semantic correlations. For solving these problems, in this paper, we propose a Bit-aware Semantic Transformer Hashing (BSTH) framework to excavate bit-wise semantic concepts and simultaneously align the heterogeneous modalities for multi-modal hash learning on the concept-level. Specifically, the bit-wise implicit semantic concepts are learned with the transformer in a self-attention manner, which can achieve implicit semantic alignment on the fine-grained concept-level and reduce the heterogeneous modality gaps. Then, the concept-level multi-modal fusion is performed to enhance the semantic representation capability of each implicit concept and the fused concept representations are further encoded to the corresponding hash bits via bit-wise hash functions. Further, to supervise the bit-aware transformer module, a label prototype learning module is developed to learn prototype embeddings for all categories that capture the explicit semantic correlations on the category-level by considering the co-occurrence priors. Experiments on three widely tested multi-modal retrieval datasets demonstrate the superiority of the proposed method from various aspects.

It is widely acknowledged that the success of deep learning is built upon large-scale training data and tremendous computing power. However, the data and computing power are not always available for many real-world applications. In this paper, we address the machine learning problem where it lacks training data and limits computing power. Specifically, we investigate domain adaptation which is able to transfer knowledge from one labeled source domain to an unlabeled target domain, so that we do not need much training data from the target domain. At the same time, we consider the situation that the running environment is confined, e.g., in edge computing the end device has very limited running resources. Technically, we present the Faster Domain Adaptation (FDA) protocol and further report two paradigms of FDA: early stopping and amid skipping. The former accelerates domain adaptation by multiple early exit points. The latter speeds up the adaptation by wisely skip several amid neural network blocks. Extensive experiments on standard benchmarks verify that our method is able to achieve the comparable and even better accuracy but employ much less computing resources. To the best of our knowledge, there are very few works which investigated accelerating knowledge adaptation in the community. This work is expected to inspire the topic for more discussion.

Recommendation efficiency and data sparsity problems have been regarded as two main challenges of real-world recommendation systems. Most existing works focus on improving recommendation accuracy instead of efficiency. In this paper, we propose a Deep Pairwise Hashing (DPH) to map users and items to binary vectors in the Hamming space, where a user's preference for an item can be efficiently calculated by the Hamming distance, which significantly improves the efficiency of online recommendation. To alleviate data sparsity and cold-start problems, the item content information exploited and integrated to learn effective representations of items. Specifically, we first pre-train robust item representation from item content data by a robust Denoising Auto-encoder instead of other deterministic deep learning frameworks. Then we fine-tune the entire recommender framework by adding a pairwise loss function with discrete constraints, which is more consistent with the ultimate goal of producing a ranked list of items. Finally, we adopt the alternating optimization method to optimize the proposed model with discrete constraints. Extensive experiments conducted on three different datasets show that DPH can significantly advance the state-of-the-art frameworks regarding data sparsity and cold-start item recommendation.

Zero-shot learning (ZSL) aims to recognize unseen classes based on the knowledge of seen classes. Previous methods focused on learning direct embeddings from global features to the semantic space in hope of knowledge transfer from seen classes to unseen classes. However, an unseen class shares local visual features with a set of seen classes and leveraging global visual features makes the knowledge transfer ineffective. To tackle this problem, we propose a Region Semantically Aligned Network (RSAN), which maps local features of unseen classes to their semantic attributes. Instead of using global features which are obtained by an average pooling layer after an image encoder, we directly utilize the output of the image encoder which maintains local information of the image. Concretely, we obtain each attribute from a specific region of the output and exploit these attributes for recognition. As a result, the knowledge of seen classes can be successfully transferred to unseen classes in a region-bases manner. In addition, we regularize the image encoder through attribute regression with a semantic knowledge to extract robust and attribute-related visual features. Experiments on several standard ZSL datasets reveal the benefit of the proposed RSAN method, outperforming state-of-the-art methods.

The number of “hits” has been widely regarded as the lifeblood of many web systems, e.g., e-commerce systems, advertising systems and multimedia consumption systems. However, users would not hit an item if they cannot see it, or they are not interested in the item. Recommender system plays a critical role of discovering interesting items from near-infinite inventory and exhibiting them to potential users. Yet, two issues are crippling the recommender systems. One is “how to handle new users”, and the other is “how to surprise users”. The former is well-known as cold-start recommendation. In this paper, we show that the latter can be investigated as long-tail recommendation. We also exploit the benefits of jointly challenging both cold-start and long-tail recommendation, and propose a novel approach which can simultaneously handle both of them in a unified objective. For the cold-start problem, we learn from side information, e.g., user attributes, user social relationships, etc. Then, we transfer the learned knowledge to new users. For the long-tail recommendation, we decompose the overall interesting items into two parts: a low-rank part for short-head items and a sparse part for long-tail items. The two parts are independently revealed in the training stage, and transfered into the final recommendation for new users. Furthermore, we effectively formulate the two problems into a unified objective and present an iterative optimization algorithm. A fast extension of the method is proposed to reduce the complexity, and extensive theoretical analysis are provided to proof the bounds of our approach. At last, experiments of social recommendation on various real-world datasets, e.g., images, blogs, videos and musics, verify the superiority of our approach compared with the state-of-the-art work.

Small data challenges have emerged in many learning problems, since the success of deep neural networks often relies on the availability of a huge number of labeled data that is expensive to collect. We explore a highly challenging task, few-sample training, which uses a small number of labeled images of each category and corresponding textual descriptions to train a model for fine-grained visual categorization. In order to tackle overfitting caused by small data, in this paper, we propose two novel feature augmentation approaches, Semantic Gate Feature Augmentation (SGFA) and Semantic Boundary Feature Augmentation (SBFA). Instead of generating a new image instance, we propose to directly synthesize instance features by leveraging semantic information, and its main novelties are: (1) The SGFA method is proposed to reduce the overfitting of small data by adding random noise to different regions of the image's feature maps through a gating mechanism. (2) The SBFA approach is proposed to optimize the decision boundary of the classifier. Technically, the decision boundary of the image feature is estimated through the assistance of semantic information, and then feature augmentation is performed by sampling in this region. Experiments in fine-grained visual categorization benchmark demonstrate that our proposed approach can significantly improve the categorization performance.

Referring expression comprehension is a task of identifying a text-related object or region in a given image by a natural language expression. In this task, it is essential to understand the expression sentence in multi-aspect and adapt it to region representations for generating the discriminative information. Unfortunately, previous approaches usually focus on the important words or phrases in the expression using self-attention mechanisms, which causes that they may fail to distinguish the target region from others, especially the similar regions. To address this problem, we propose a novel model, termed Multi-level Expression Guided Attention network (MEGA-Net). It contains a multi-level visual attention schema guided by the expression representations in different levels, i.e., sentence-level, word-level and phrase-level, which allows generating the discriminative region features and helps to locate the related regions accurately. In addition, to distinguish the similar regions, we design a two-stage structure, where we first select top-K candidate regions according to their matching scores in the first stage, then we apply an object comparison attention mechanism to learn the difference between the candidates for matching the target region. We evaluate the proposed approach on three popular benchmark datasets and the experimental results demonstrate that our model performs against state-of-the-art methods.

Cross-modal retrieval aims at enabling flexible retrieval across different modalities. The core of cross-modal retrieval is to learn projections for different modalities and make instances in the learned common subspace comparable to each other. Self-supervised learning automatically creates a supervision signal by transformation of input data and learns semantic features by training to predict the artificial labels. In this paper, we proposed a novel method named Self-Supervised Adversarial Learning (SSAL) for Cross-Modal Retrieval, which deploys self-supervised learning and adversarial learning to seek an effective common subspace. A feature projector tries to generate modality-invariant representations in the common subspace that can confuse an adversarial discriminator consists of two classifiers. One of the classifiers aims to predict rotation angle from image representations, while the other classifier tries to discriminate between different modalities from the learned embeddings. By confusing the self-supervised adversarial model, feature projector filters out the abundant high-level visual semantics and learns image embeddings that are better aligned with text modality in the common subspace. Through the joint exploitation of the above, an effective common subspace is learned, in which representations of different modlities are aligned better and common information of different modalities is well preserved. Comprehensive experimental results on three widely-used benchmark datasets show that the proposed method is superior in cross-modal retrieval and significantly outperforms the existing cross-modal retrieval methods.

Multi-modal hashing methods could support efficient multimedia retrieval by combining multi-modal features for binary hash learning at the both offline training and online query stages. However, existing multi-modal methods cannot binarize the queries, when only one or part of modalities are provided. In this article, we propose a novel Flexible Multi-modal Hashing (FMH) method to address this problem. FMH learns multiple modality-specific hash codes and multi-modal collaborative hash codes simultaneously within a single model. The hash codes are flexibly generated according to the newly coming queries, which provide any one or combination of modality features. Besides, the hashing learning procedure is efficiently supervised by the pair-wise semantic matrix to enhance the discriminative capability. It could successfully avoid the challenging symmetric semantic matrix factorization and O ( n 2 ) storage cost of semantic matrix. Finally, we design a fast discrete optimization to learn hash codes directly with simple operations. Experiments validate the superiority of the proposed approach.

Many achievements have been made on learning to hash for uni-modal and cross-modal retrieval. However, it is still an unsolved problem that how to directly and efficiently learn discriminative discrete hash codes for the multimedia retrieval, where both query and database samples are represented with heterogeneous multi-modal features. With this motivation, we propose a Fast Discrete Collaborative Multi-modal Hashing (FDCMH) method in this paper. We first propose an efficient collaborative multi-modal mapping that first transforms heterogeneous multi-modal features into the unified factors to exploit the complementarity of multi-modal features and preserve the semantic correlations in multiple modalities with linear computation and space complexity. Such shared factors also bridge the heterogeneous modality gap and remove the inter-modality redundancy. Further, we develop an asymmetric hashing learning module to simultaneously correlate the learned hash codes with low-level data distribution and high-level semantics. In particular, this design could avoid the challenging symmetric semantic matrix factorization and O(n2) memory cost (n is the number of training samples). It can support both computation and memory efficient discrete hash optimization. Experiments on several public multimedia retrieval datasets demonstrate the superiority of the proposed approach compared with state-of-the-art hashing techniques, in terms of both model learning efficiency and retrieval accuracy.

Different from the traditional recommender system, the session-based recommender system introduces the concept of the session , i.e., a sequence of interactions between a user and multiple items within a period, to preserve the user’s recent interest. The existing work on the session-based recommender system mainly relies on mining sequential patterns within individual sessions, which are not expressive enough to capture more complicated dependency relationships among items. In addition, it does not consider the cross-session information due to the anonymity of the session data, where the linkage between different sessions is prevented. In this article, we solve these problems with the graph neural networks technique. First, each session is represented as a graph rather than a linear sequence structure, based on which a novel F ull G raph N eural N etwork (FGNN) is proposed to learn complicated item dependency. To exploit and incorporate cross-session information in the individual session’s representation learning, we further construct a B roadly C onnected S ession (BCS) graph to link different sessions and a novel Mask-Readout function to improve session embedding based on the BCS graph. Extensive experiments have been conducted on two e-commerce benchmark datasets, i.e., Yoochoose and Diginetica , and the experimental results demonstrate the superiority of our proposal through comparisons with state-of-the-art session-based recommender models.

Predicting a user's preference in a short anonymous interaction session instead of long-term history is a challenging problem in the real-life session-based recommendation, e.g., e-commerce and media stream. Recent research of the session-based recommender system mainly focuses on sequential patterns by utilizing the attention mechanism, which is straightforward for the session's natural sequence sorted by time. However, the user's preference is much more complicated than a solely consecutive time pattern in the transition of item choices. In this paper, therefore, we study the item transition pattern by constructing a session graph and propose a novel model which collaboratively considers the sequence order and the latent order in the session graph for a session-based recommender system. We formulate the next item recommendation within the session as a graph classification problem. Specifically, we propose a weighted attention graph layer and a Readout function to learn embeddings of items and sessions for the next item recommendation. Extensive experiments have been conducted on two benchmark E-commerce datasets, Yoochoose and Diginetica, and the experimental results show that our model outperforms other state-of-the-art methods.

Most existing Zero-Shot Learning (ZSL) approaches adopt the semantic space as a bridge to classify unseen categories. However, it is difficult to transfer knowledge from seen categories to unseen categories through semantic space, since the correlations among categories are uncertain and ambiguous in the semantic space. In this paper, we formulated zero-shot learning as a classifier weight regression problem. Specifically, we propose a novel Residual Graph Convolution Network (ResGCN) which takes word embeddings and knowledge graph as inputs and outputs a visual classifier for each category. ResGCN can effectively alleviate the problem of over-smoothing and over-fitting. During the test, an unseen image can be classified by ranking the inner product of its visual feature and predictive visual classifiers. Moreover, we provide a new method to build a better knowledge graph. Our approach not only further enhances the correlations among categories, but also makes it easy to add new categories to the knowledge graph. Experiments conducted on the large-scale ImageNet 2011 21K dataset demonstrate that our method significantly outperforms existing state-of-the-art approaches.