Reinforcement learning (RL) has shown great promise in optimizing long-term user interest in recommender systems. However, existing RL-based recommendation methods need a large number of interactions for each user to learn the recommendation policy. The challenge becomes more critical when recommending to new users who have a limited number of interactions. To that end, in this article, we address the cold-start challenge in the RL-based recommender systems by proposing a novel context-aware offline meta-level model-based RL approach for user adaptation. Our proposed approach learns to infer each user's preference with a user context variable that enables recommendation systems to better adapt to new users with limited contextual information. To improve adaptation efficiency, our approach learns to recover the user choice function and reward from limited contextual information through an inverse RL method, which is used to assist the training of a meta-level recommendation agent. To avoid the need for online interaction, the proposed method is trained using historically collected offline data. Moreover, to tackle the challenge of offline policy training, we introduce a mutual information constraint between the user model and recommendation agent. Evaluation results show the superiority of our developed offline policy learning method when adapting to new users with limited contextual information. In addition, we provide a theoretical analysis of the recommendation performance bound.

The recent breakthrough achieved by graph neural networks (GNNs) with few labeled data accelerates the pace of deploying GNNs on real-world applications. While several efforts have been made to scale GNNs training for large-scale graphs, GNNs still suffer from the scalability challenge of model inference, due to the graph dependency issue incurred by the message-passing mechanism, therefore hindering its deployment in resource-constrained applications. An intuitive remedy is compressing the cumbersome GNN model into inference-friendly multi-layer perceptrons (MLPs) using knowledge distillation (KD). However, the standard KD strategy, i.e., training MLPs using the soft labels of labeled and unlabeled nodes from the teacher, is suboptimal, since the GNN teacher would inevitably make wrong predictions for unlabeled data, especially in the semi-supervised scenario. To address this, we propose a novel Reliable Knowledge Distillation framework for MLP optimization (RKDMLP), which shows strong promise in achieving a “sweet point” in co-optimizing model accuracy and efficiency. Its core insight is to use a meta-policy to filter out those unreliable soft labels. To train the meta-policy, we design a reward-driven objective based on a meta-set and adopt policy gradient to optimize the expected reward. Then we apply the meta-policy to the unlabeled nodes and select the most reliable soft labels for distillation. Extensive experiments across various GNN backbones, on 7 small graphs and 2 large-scale datasets from the challenging Open Graph Benchmark, demonstrate the superiority of our proposal. Moreover, RKD-MLP also shows good robustness iv.r.t. graph topology and node feature noises.

Graph neural networks (GNNs), which learn the node representations by recursively aggregating information from its neighbors, have become a predominant computational tool in many domains. To handle large-scale graphs, most of the existing methods partition the input graph into multiple sub-graphs (e.g., through node clustering) and apply batch training to save memory cost. However, such batch training will lead to label bias within each batch and result in over- confidence in model predictions. Since the connected nodes with positively related labels tend to be assigned together, the traditional cross-entropy minimization process attends on the predictions of biased classes at a batch to intensify the overfitting issue. To overcome the problem of label bias, we propose adaptive label smoothing (ALS) method to replace the one-hot hard labels with smoothed ones, which learns to allocate label confidences from the biased classes to the others. Specifically, ALS propagates node labels to aggregate the neighborhood label distribution in a pre-processing step, and then updates the optimal smoothed labels online to adapt to specific graph structure. Experiments on the real-world datasets demonstrate that ALS can be generally applied to the main scalable learning frameworks to calibrate the biased labels and improve generalization performances.

Self-supervised learning (SSL) has been demonstrated to be effective in pre-training models that can be generalized to various downstream tasks. Graph Autoencoder (GAE), an increasingly popular SSL approach on graphs, has been widely explored to learn node representations without ground-truth labels. However, recent studies show that existing GAE methods could only perform well on link prediction tasks, while their performance on classification tasks is rather limited. This limitation casts doubt on the generalizability and adoption of GAE. In this paper, for the first time, we show that GAE can generalize well to both link prediction and classification scenarios, including node-level and graph-level tasks, by redesigning its critical building blocks from the graph masking perspective. Our proposal is called Self-Supervised Graph Autoencoder--S2GAE, which unleashes the power of GAEs with minimal yet nontrivial efforts. Specifically, instead of reconstructing the whole input structure, we randomly mask a portion of edges and learn to reconstruct these missing edges with an effective masking strategy and an expressive decoder network. Moreover, we theoretically prove that S2GAE could be regarded as an edge-level contrastive learning framework, providing insights into why it generalizes well. Empirically, we conduct extensive experiments on 21 benchmark datasets across link prediction and node & graph classification tasks. The results validate the superiority of S2GAE against state-of-the-art generative and contrastive methods. This study demonstrates the potential of GAE as a universal representation learner on graphs. Our code is publicly available at https://github.com/qiaoyu-tan/S2GAE.

Graph neural networks (GNNs) have received remarkable success in link prediction (GNNLP) tasks. Existing efforts first predefine the subgraph for the whole dataset and then apply GNNs to encode edge representations by leveraging the neighborhood structure induced by the fixed subgraph. The prominence of GNNLP methods significantly relies on the adhoc subgraph. Since node connectivity in real-world graphs is complex, one shared subgraph is limited for all edges. Thus, the choices of subgraphs should be personalized to different edges. However, performing personalized subgraph selection is nontrivial since the potential selection space grows exponentially to the scale of edges. Besides, the inference edges are not available during training in link prediction scenarios, so the selection process needs to be inductive. To bridge the gap, we introduce a Personalized Subgraph Selector (PS2) as a plug-and-play framework to automatically, personally, and inductively identify optimal subgraphs for different edges when performing GNNLP. PS2 is instantiated as a bi-level optimization problem that can be efficiently solved differently. Coupling GNNLP models with PS2, we suggest a brand-new angle towards GNNLP training: by first identifying the optimal subgraphs for edges; and then focusing on training the inference model by using the sampled subgraphs. Comprehensive experiments endorse the effectiveness of our proposed method across various GNNLP backbones (GCN, GraphSage, NGCF, LightGCN, and SEAL) and diverse benchmarks (Planetoid, OGB, and Recommendation datasets). Our code is publicly available at https://github.com/qiaoyu-tan/PS2

In practical recommendation scenarios, users often interact with items under multi-typed behaviors (e.g., click, add-to-cart, and purchase). Traditional collaborative filtering techniques typically assume that users only have a single type of behavior with items, making it insufficient to utilize complex collaborative signals to learn informative representations and infer actual user preferences. Consequently, some pioneer studies explore modeling multi-behavior heterogeneity to learn better representations and boost the performance of recommendations for a target behavior. However, a large number of auxiliary behaviors (i.e., click and add-to-cart) could introduce irrelevant information to recommenders, which could mislead the target behavior (i.e., purchase) recommendation, rendering two critical challenges: (i) denoising auxiliary behaviors and (ii) bridging the semantic gap between auxiliary and target behaviors. Motivated by the above observation, we propose a novel framework–Denoising and Prompt-Tuning (DPT) with a three-stage learning paradigm to solve the aforementioned challenges. In particular, DPT is equipped with a pattern-enhanced graph encoder in the first stage to learn complex patterns as prior knowledge in a data-driven manner to guide learning informative representation and pinpointing reliable noise for subsequent stages. Accordingly, we adopt different lightweight tuning approaches with effectiveness and efficiency in the following stages to further attenuate the influence of noise and alleviate the semantic gap among multi-typed behaviors. Extensive experiments on two real-world datasets demonstrate the superiority of DPT over a wide range of state-of-the-art methods. The implementation code is available online at https://github.com/zc-97/DPT.

Sequential recommender systems aim to recommend the next items in which target users are most interested based on their historical interaction sequences. In practice, historical sequences typically contain some inherent noise (e.g., accidental interactions), which is harmful to learn accurate sequence representations and thus misleads the next-item recommendation. However, the absence of supervised signals (i.e., labels indicating noisy items) makes the problem of sequence denoising rather challenging. To this end, we propose a novel sequence denoising paradigm for sequential recommendation by learning hierarchical item inconsistency signals. More specifically, we design a hierarchical sequence denoising (HSD) model, which first learns two levels of inconsistency signals in input sequences, and then generates noiseless subsequences (i.e., dropping inherent noisy items) for subsequent sequential recommenders. It is noteworthy that HSD is flexible to accommodate supervised item signals, if any, and can be seamlessly integrated with most existing sequential recommendation models to boost their performance. Extensive experiments on five public benchmark datasets demonstrate the superiority of HSD over state-of-the-art denoising methods and its applicability over a wide variety of mainstream sequential recommendation models. The implementation code is available at https://github.com/zc-97/HSD

As an emerging paradigm, session-based recommendation is aimed at recommending the next item based on a set of anonymous sessions. Effectively representing a session that is normally a short interaction sequence renders a major technical challenge. In view of the limitations of pioneering studies that explore collaborative information from other sessions, in this paper we propose a new direction to enhance session representations by learning multi-faceted session-independent global item relations. In particular, we identify three types of advantageous global item relations, including negative relations that have not been studied before, and propose different graph construction methods to capture such relations. We then devise a novel multi-faceted global item relation (MGIR) model to encode different relations using different aggregation layers and generate enhanced session representations by fusing positive and negative relations. Our solution is flexible to accommodate new item relations and can easily integrate existing session representation learning methods to generate better representations from global relation enhanced session information. Extensive experiments on three benchmark datasets demonstrate the superiority of our model over a large number of state-of-the-art methods. Specifically, we show that learning negative relations is critical for session-based recommendation.

Recommender systems play a fundamental role in web applications in filtering massive information and matching user interests. While many efforts have been devoted to developing more effective models in various scenarios, the exploration on the explainability of recommender systems is running behind. Explanations could help improve user experience and discover system defects. In this paper, after formally introducing the elements that are related to model explainability, we propose a novel explainable recommendation model through improving the transparency of the representation learning process. Specifically, to overcome the representation entangling problem in traditional models, we revise traditional graph convolution to discriminate information from different layers. Also, each representation vector is factorized into several segments, where each segment relates to one semantic aspect in data. Different from previous work, in our model, factor discovery and representation learning are simultaneously conducted, and we are able to handle extra attribute information and knowledge. In this way, the proposed model can learn interpretable and meaningful representations for users and items. Unlike traditional methods that need to make a trade-off between explainability and effectiveness, the performance of our proposed explainable model is not negatively affected after considering explainability. Finally, comprehensive experiments are conducted to validate the performance of our model as well as explanation faithfulness.

Real-time bidding (RTB) that features perimpression-level real-time ad auctions has become a popular practice in today's digital advertising industry. In RTB, click-through rate (CTR) prediction is a fundamental problem to ensure the success of an ad campaign and boost revenue. In this paper, we present a dynamic CTR prediction model designed for the Samsung demand-side platform (DSP). From our production data, we identify two key technical challenges that have not been fully addressed by the existing solutions: the dynamic nature of RTB and user information scarcity. To address both challenges, we develop a Dynamic Neural Network model. Our model effectively captures the dynamic evolutions of both users and ads and integrates auxiliary data sources (e.g., installed apps) to better model users' preferences. We put forward a novel interaction layer that fuses both explicit user responses (e.g., clicks on ads) and auxiliary data sources to generate consolidated user preference representations. We evaluate our model using a large amount of data collected from the Samsung advertising platform and compare our method against several state-of-the-art methods that are likely suitable for real-world deployment. The evaluation results demonstrate the effectiveness of our method and the potential for production. In addition, we discuss how to address a few practical engineering challenges caused by big data toward making our model in readiness for deployment.