Federated learning (FL) has received much attention in privacy-preserving and responsible recommender systems. Recent studies have shown promising results while federating widely used recommendation methods such as collaborative filtering. A major barrier when bringing FL into production is that the model complexity or the volume of gradients to be transmitted over the communication channel grows linearly as the number of items in a particular system increases. To address this challenge, we propose a communication-efficient neural collaborative filtering method for federated recommender systems. First, to align our solution with other deep neural architectures, we construct standard neural collaborative filtering in federated settings. Second, to solve the underlying model complexity challenge, a multi-armed bandit framework is used that intelligently selects a smaller set of payloads for each iteration of federated model training. The item selection is based on a carefully designed reward function that determines which portion of the overall payloads would be optimal for a particular user. The FL model only comprising of the selected items is transmitted over the network. The FL users train their local models in the regular federated learning way utilizing the payload-efficient global model, requiring no additional optimizations. The results show that using only 10% of the model’s payload, our method can achieve recommendation performance comparable with the standard federated neural collaborative filtering.

Discovering user preferences across different domains is pivotal in cross-domain recommendation systems, particularly when platforms lack comprehensive user-item interactive data. The limited presence of shared users often hampers the effective modeling of common preferences. While leveraging shared items’ attributes, such as category and popularity, can enhance cross-domain recommendation performance, the scarcity of shared items between domains has limited research in this area. To address this, we propose a Coherence-guided Preference Disentanglement (CoPD) method aimed at improving cross-domain recommendation by (i) explicitly extracting shared item attributes to guide the learning of shared user preferences and (ii) disentangling these preferences to identify specific user interests transferred between domains. CoPD introduces coherence constraints on item embeddings of shared and specific domains, aiding in extracting shared attributes. Moreover, it utilizes these attributes to guide the disentanglement of user preferences into separate embeddings for interest and conformity through a popularity-weighted loss. Experiments conducted on real-world datasets demonstrate the superior performance of our proposed CoPD over existing competitive baselines, highlighting its effectiveness in enhancing cross-domain recommendation performance. The code is available at https://github.com/XiangZongyi/CoPD .

Cold-start has become critical for recommendations, especially for sparse user-item interactions. Recent approaches based on meta-learning succeed in alleviating the issue, owing to the fact that these methods have strong generalization, so they can fast adapt to new tasks under cold-start settings. However, these meta-learning-based recommendation models learned with single and spase ratings are easily falling into the meta-overfitting, since the one and only rating$r_{ui}$to a specific item$i$cannot reflect a user's diverse interests under various circumstances(e.g., time, mood, age, etc), i.e. if$r_{ui}$equals to 1 in the historical dataset, but$r_{ui}$could be 0 in some circumstance. In meta-learning, tasks with these single ratings are called Non-Mutually-Exclusive(Non-ME) tasks, and tasks with diverse ratings are called Mutually-Exclusive(ME) tasks. Fortunately, a meta-augmentation technique is proposed to relief the meta-overfitting for meta-learning methods by transferring Non-ME tasks into ME tasks by adding noises to labels without changing inputs. Motivated by the meta-augmentation method, in this paper, we propose a cross-domain meta-augmentation technique for content-aware recommendation systems (MetaCAR) to construct ME tasks in the recommendation scenario. Our proposed method consists of two stages: meta-augmentation and meta-learning. In the meta-augmentation stage, we first conduct domain adaptation by a dual conditional variational autoencoder (CVAE) with a multi-view information bottleneck constraint, and then apply the learned CVAE to generate ratings for users in the target domain. In the meta-learning stage, we introduce both the true and generated ratings to construct ME tasks that enables the meta-learning recommendations to avoid meta-overfitting. Experiments evaluated in real-world datasets show the significant superiority of MetaCAR for coping with the cold-start user issue over competing baselines including cross-domain, content-aware, and meta-learning-based recommendations.

Secure transfer of wireless information is becoming a critical issue in multi-user interference networks. In this paper, we consider secure transmission from a source (Alice) to a legitimate destination (Bob), coexisting with a passive eaves-dropper (Eve) and$K$transceiver pairs. By assuming that only statistical channel state information (CSI) of Eve and local CSIs of legitimate users are known, a secrecy beamforming scheme with artificial noise (AN) is designed for secure transmission, and a modified interference alignment (IA) scheme is proposed for secrecy enhancement. Unlike the conventional AN-aided IA approaches which may lead to private signal cancellation, we propose a novel design modification with security protection. Moreover, a definite connection between improperness and in-feasibility of IA is established, to provide guiding insights on IA requirements. Based on a strict mathematical analysis, we further characterize the impact of transmit power on transceiver design and secrecy performance. Numerical results confirm that our design enables high transmission security with performance guarantee, and thus is suitable and stable for physical layer security (PLS) in multi-user interference networks.

Cold-start issues have been more and more challenging for providing accurate recommendations with the fast increase of users and items. Most existing approaches attempt to solve the intractable problems via content-aware recommendations based on auxiliary information and/or cross-domain recommendations with transfer learning. Their performances are often constrained by the extremely sparse user-item interactions, unavailable side information, or very limited domain-shared users. Recently, meta-learners with meta-augmentation by adding noises to labels have been proven to be effective to avoid overfitting and shown good performance on new tasks. Motivated by the idea of meta-augmentation, in this paper, by treating a user's preference over items as a task, we propose a so-called Diverse Preference Augmentation framework with multiple source domains based on meta-learning (referred to as MetaDPA) to i) generate diverse ratings in a new domain of interest (known as target domain) to handle overfitting on the case of sparse interactions, and to ii) learn a preference model in the target domain via a meta-learning scheme to alleviate cold-start issues. Specifically, we first conduct multi-source domain adaptation by dual conditional variational autoencoders and impose a Multi-domain InfoMax (MDI) constraint on the latent representations to learn domain-shared and domain-specific preference properties. To avoid overfitting, we add a Mutually-Exclusive (ME) constraint on the output of decoders to generate diverse ratings given content data. Finally, these generated diverse ratings and the original ratings are introduced into the meta-training procedure to learn a preference meta-learner, which produces good generalization ability on cold-start recommendation tasks. Experiments on real-world datasets show our proposed MetaDPA clearly outperforms the current state-of-the-art baselines.

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.

Videos flow as the mixture of language, acoustic, and vision modalities. A thorough video understanding needs to fuse time-series data of different modalities for prediction. Due to the variable receiving frequency for sequences from each modality, there usually exists inherent asynchrony across the collected multimodal streams. Towards an efficient multimodal fusion from asynchronous multimodal streams, we need to model the correlations between elements from different modalities. The recent Multimodal Transformer (MulT) approach extends the self-attention mechanism of the original Transformer network to learn the crossmodal dependencies between elements. However, the direct replication of self-attention will suffer from the distribution mismatch across different modality features. As a result, the learnt crossmodal dependencies can be unreliable. Motivated by this observation, this work proposes the Modality-Invariant Crossmodal Attention (MICA) approach towards learning crossmodal interactions over modality-invariant space in which the distribution mismatch between different modalities is well bridged. To this end, both the marginal distribution and the elements with high-confidence correlations are aligned over the common space of the query and key vectors which are computed from different modalities. Experiments on three standard benchmarks of multimodal video understanding clearly validate the superiority of our approach.

The efficiency of top-k recommendation is vital to large-scale recommender systems. Hashing is not only an efficient alternative but also complementary to distributed computing, and also a practical and effective option in a computing environment with limited resources. Hashing techniques improve the efficiency of online recommendation by representing users and items by binary codes. However, objective functions of existing methods are not consistent with ultimate goals of recommender systems, and are often optimized via discrete coordinate descent, easily getting stuck in a local optimum. To this end, we propose a Discrete Ranking-based Matrix Factorization (DRMF) algorithm based on each user's pairwise preferences, and formulate it into binary quadratic programming problems to learn binary codes. Due to non-convexity and binary constraints, we further propose self-paced learning for improving the optimization, to include pairwise preferences gradually from easy to complex. We finally evaluate the proposed algorithm on three public real-world datasets, and show that the proposed algorithm outperforms the state-of-the-art hashing-based recommendation algorithms, and even achieves comparable performance to matrix factorization methods.

Cold-start problem and recommendation efficiency have been regarded as two crucial challenges in the recommender system. In this paper, we propose a hashing based deep learning framework called Discrete Deep Learning (DDL), to map users and items to Hamming space, where a user»s preference for an item can be efficiently calculated by Hamming distance, and this computation scheme significantly improves the efficiency of online recommendation. Besides, DDL unifies the user-item interaction information and the item content information to overcome the issues of data sparsity and cold-start. To be more specific, to integrate content information into our DDL framework, a deep learning model, Deep Belief Network (DBN), is applied to extract effective item representation from the item content information. Besides, the framework imposes balance and irrelevant constraints on binary codes to derive compact but informative binary codes. Due to the discrete constraints in DDL, we propose an efficient alternating optimization method consisting of iteratively solving a series of mixed-integer programming subproblems. Extensive experiments have been conducted to evaluate the performance of our DDL framework on two different Amazon datasets, and the experimental results demonstrate the superiority of DDL over the state-of-the-art methods regarding online recommendation efficiency and cold-start recommendation accuracy.

Personalized ranking is usually considered as an ultimate goal of recommendation systems, but it suffers from efficiency issues when making recommendations. To this end, we propose a learning-based hashing framework called Discrete Personalized Ranking (DPR), to map users and items to a Hamming space, where user-item affinity can be efficiently calculated via Hamming distance. Due to the existence of discrete constraints, it is possible to exploit a two-stage learning procedure for learning binary codes according to most existing methods. This two-stage procedure consists of relaxed optimization by discarding discrete constraints and subsequent binary quantization. However, such a procedure has been shown resulting in a large quantization loss, so that longer binary codes would be required. To this end, DPR directly tackles the discrete optimization problem of personalized ranking. And the balance and un-correlation constraints of binary codes are imposed to derive compact but informatics binary codes. Based on the evaluation on several datasets, the proposed framework shows consistent superiority to the competing baselines even though only using shorter binary code.

Recommendation is widely used to deal with information overloading by suggesting items based on historical information of users. One of the most popular recommendation techniques is matrix factorization (MF), in which the preferences of users are estimated by dot products of their real latent factors between users and items. Although MF can achieve high recommendation accuracy, it suffers from efficiency issues when making preferences ranking in real space. Hash retrieval technique can be applied to recommender systems to speed up preferences ranking. Due to the existence of discrete constraints in learning hash codes, it is possible to exploit a two-stage learning procedure according to most existing methods. This two-stage procedure consists of relaxed optimization by discarding discrete constraints and subsequent binary quantization. However, existing methods have not been able to well handle the change of dot product arising from quantization. To this end, we propose a dot-product based preference preserved hashing method, which quantizes both norm and cosine similarity in dot product respectively. We also design an algorithm to optimize the bit length for norm quantization. Based on the evaluation to several datasets, the proposed framework shows consistent superiority to the competing baselines even though only using shorter binary code.

Recommender systems have been widely used to deal with information overload, by suggesting relevant items that match users' personal interest. One of the most popular recommendation techniques is matrix factorization (MF). The inner products of learned latent factors between users and items can estimate users' preferences for items with high accuracy, but the preferences ranking is time consuming. Thus, hashing-based fast search technologies were exploited in recommender systems. However, most previous approaches consist of two stages: continuous latent factor learning and binary quantization, but they didn't well deal with the change of inner product arising from quantization. To this end, in this paper, we propose a constraint free preference preserving hashing method, which quantizes both norm and similarity in dot product. We also design an algorithm to optimize the bit length for norm quantization. The performance of our method is evaluated on three real world datasets. The results confirm that the proposed model can improve recommendation performance by 11%-15%, as compared with the state-of-the-art hashing approaches.

Affine equivalence classification of Boolean functions has significant applications in logic synthesis and cryptography. Previous studies for classification have been limited by the large set of Boolean functions and the complex operations on the affine group. Although there are many research on affine equivalence classification for parts of Boolean functions in recent years, there are very few results for the entire set of Boolean functions. The best existing result has been achieved by Harrison with 15768919 affine equivalence classes for 6-variable Boolean functions. This paper presents a concise formula for affine equivalence classification of the entire set of Boolean functions as well as a formula for affine classification of Boolean functions with distinct ON-set size respectively. The method outlined in this paper greatly simplifies the affine group's action by constructing an isomorphism mapping from the affine group to a permutation group. By this method, we can compute the affine equivalence classes for up to 10 variables. Experiment results indicate that our scheme for calculating the affine equivalence classes for more than 6 variables is a significant advancement over previous published methods.