Many platforms, such as e-commerce websites, offer both search and recommendation services simultaneously to better meet users' diverse needs. Recommendation services suggest items based on user preferences, while search services allow users to search for items before providing recommendations. Since users and items are often shared between the search and recommendation domains, there is a valuable opportunity to enhance the recommendation domain by leveraging user preferences extracted from the search domain. Existing approaches either overlook the shift in user intention between these domains or fail to capture the significant impact of learning from users' search queries on understanding their interests.

Multi-types of user behavior data (e.g., clicking, adding to cart, and purchasing) are recorded in most real-world recommendation scenarios, which can help to learn users’ multi-faceted preferences. However, it is challenging to explore multi-behavior data due to the unbalanced data distribution and sparse target behavior, which lead to the inadequate modeling of high-order relations when treating multi-behavior data “as features” and gradient conflict in multi-task learning when treating multi-behavior data “as labels”. In this paper, we propose CIGF, a Compressed Interaction Graph based Framework, to overcome the above limitations. Specifically, we design a novel Compressed Interaction Graph Convolution Network (CIGCN) to model instance-level high-order relations explicitly. To alleviate the potential gradient conflict when treating multi-behavior data “as labels”, we propose a Multi-Expert with Separate Input (MESI) network with separate input on the top of CIGCN for multi-task learning. Comprehensive experiments on three large-scale real-world datasets demonstrate the superiority of CIGF.

Graph Convolutional Neural Networks (GNN) based recommender systems are state-of-the-art since they can capture the high order collaborative signals between users and items. However, they suffer from the feature leakage problem since label information determined by edges can be leaked into node embeddings through the GNN aggregation procedure guided by the same set of edges, leading to poor generalization. We propose the accurate removal algorithm to generate the final embedding. For each edge, the embeddings of the two end nodes are evaluated on a graph with that edge removed. We devise an algebraic trick to efficiently compute this procedure without explicitly constructing separate graphs for the LightGCN model. Experiments on four datasets demonstrate that our algorithm can perform better on datasets with sparse interactions, while the training time is significantly reduced.

Methods that learn representations of nodes in a graph play an important role in network analysis. Most of the existing methods of graph representation learning have focused on embedding each node in a graph as a single vector in a low-dimensional continuous space. However, these methods have a crucial limitation: the lack of modeling the uncertainty about the representation. In this work, inspired by Adversarial Variational Bayes (AVB) [22], we propose GraphAVB, a probabilistic generative model to learn node representations that preserve connectivity patterns and capture the uncertainties in the graph. Unlike Graph2Gauss [3] deep which embeds each node as a Gaussian distribution, we represent each node as an implicit distribution parameterized by a neural network in the latent space, which is more flexible and expressive to capture the complex uncertainties in real-world graph-structured datasets. To perform the designed variational inference algorithm with neural samplers, we introduce an auxiliary discriminative network that is used to infer the log probability ratio terms in the objective function and allows us to cast maximizing the objective function as a two-player game. Experimental results on multiple real-world graph datasets demonstrate the effectiveness of our proposed method GraphAVB, outperforming many competitive baselines on the task of link prediction. The superior performances of our proposed method GraphAVB also demonstrate that the downstream tasks can benefit from the captured uncertainty.

Personalized recommender systems are playing an increasingly important role for online consumption platforms. Because of the multitude of relationships existing in recommender systems, Graph Neural Networks (GNNs) based approaches have been proposed to better characterize the various relationships between a user and items while modeling a user's preferences. Previous graph-based recommendation approaches process the observed user-item interaction graph as a ground-truth depiction of the relationships between users and items. However, especially in the implicit recommendation setting, all the unobserved user-item interactions are usually assumed to be negative samples. There are missing links that represent a user's future actions. In addition, there may be spurious or misleading positive interactions. To alleviate the above issue, in this work, we take a first step to introduce a principled way to model the uncertainty in the user-item interaction graph using the Bayesian Graph Convolutional Neural Network framework. We discuss how inference can be performed under our framework and provide a concrete formulation using the Bayesian Probabilistic Ranking training loss. We demonstrate the effectiveness of our proposed framework on four benchmark recommendation datasets. The proposed method outperforms state-of-the-art graph-based recommendation models. Furthermore, we conducted an offline evaluation on one industrial large-scale dataset. It shows that our proposed method outperforms the baselines, with the potential gain being more significant for cold-start users. This illustrates the potential practical benefit in real-world recommender systems.

Most current distributed machine learning systems try to scale up model training by using a data-parallel architecture that divides the computation for different samples among workers. We study distributed machine learning from a different motivation, where the information about the same samples, e.g., users and objects, are owned by several parities that wish to collaborate but do not want to share raw data with each other.

User action modeling and prediction has long been a topic of importance to recommender systems and user profiling. The quality of the model or accuracy of prediction plays a vital role in related applications like recommendation, advertisement displaying, searching, etc. For large scale systems with a massive number of users, beside the pure prediction performance, there are other practical factors like training and prediction latency, memory overhead, that must be optimized to ensure smooth operation of the system. We propose a fast linear computational framework to handle a vast number of second order crossed features with dimensionality reduction. By leveraging the training and serving system architecture, we shift heavy calculation burden from online serving to offline preprocessing, at the cost of a reasonable amount of memory overhead. The experiments on a 15-day data trace from Tencent MyApp shows that our proposed framework can achieve comparable prediction performance to much complex models like the field-aware factorization machine (FFM) while being served in 2 ms with a reasonable amount of memory overhead.