Interactive recommendation is a typical information-seeking task that allows users to interactively express their needs through natural language and obtain personalized recommendations. Large language model-powered (LLM-powered) agents have become a new paradigm in interactive recommendations, effectively capturing users' real-time needs and enhancing personalized experiences. However, due to limited planning and generalization capabilities, existing formulations of LLM-powered interactive recommender agents struggle to effectively address diverse and complex user intents, such as intuitive, unrefined, or occasionally ambiguous requests. To tackle this challenge, we propose a novel thought-augmented interactive recommender agent system (TAIRA) that addresses complex user intents through distilled thought patterns. Specifically, TAIRA is designed as an LLM-powered multi-agent system featuring a manager agent that orchestrates recommendation tasks by decomposing user needs and planning subtasks, with its planning capacity strengthened through Thought Pattern Distillation (TPD), a thought-augmentation method that extracts high-level thoughts from the agent's and human experts' experiences. Moreover, we designed a set of user simulation schemes to generate personalized queries of different difficulties and evaluate the recommendations based on specific datasets. Through comprehensive experiments conducted across multiple datasets, TAIRA exhibits significantly enhanced performance compared to existing methods. Notably, TAIRA shows a greater advantage on more challenging tasks while generalizing effectively on novel tasks, further validating its superiority in managing complex user intents within interactive recommendation systems. The code is publicly available at:https://github.com/Alcein/TAIRA.
Interactive Recommendation (IR) has gained significant attention recently for its capability to quickly capture dynamic interest and optimize both short and long term objectives. IR agents are typically implemented through Deep Reinforcement Learning (DRL), because DRL is inherently compatible with the dynamic nature of IR. However, DRL is currently not perfect for IR. Due to the large action space and sample inefficiency problem, training DRL recommender agents is challenging. The key point is that useful features cannot be extracted as high-quality representations for the recommender agent to optimize its policy. To tackle this problem, we propose Contrastive Representation for Interactive Recommendation (CRIR). CRIR efficiently extracts latent, high-level preference ranking features from explicit interaction, and leverages the features to enhance users' representation. Specifically, the CRIR provides representation through one representation network, and refines it through our proposed Preference Ranking Contrastive Learning (PRCL). The key insight of PRCL is that it can perform contrastive learning without relying on computations involving high-level representations or large potential action sets. Furthermore, we also propose a data exploiting mechanism and an agent training mechanism to better adapt CRIR to the DRL backbone. Extensive experiments have been carried out to show our method's superior improvement on the sample efficiency while training an DRL-based IR agent.
Weblogs, comprised of records detailing user activities on any website, offer valuable insights into user preferences, behavior, and interests. Numerous recommendation algorithms, employing strategies such as collaborative filtering, content-based filtering, and hybrid methods, leverage the data mined through these weblogs to provide personalized recommendations to users. Despite the abundance of information available in these weblogs, identifying and extracting pertinent information and key features from them necessitate extensive engineering endeavors. The intricate nature of the data also poses a challenge for interpretation, especially for non-experts. In this study, we introduce a sophisticated and interactive recommendation framework denoted as InteraRec, which diverges from conventional approaches that exclusively depend on weblogs for recommendation generation. InteraRec framework captures high-frequency screenshots of web pages as users navigate through a website. Leveraging state-of-the-art multimodal large language models (MLLMs), it extracts valuable insights into user preferences from these screenshots by generating a textual summary based on predefined keywords. Subsequently, an LLM-integrated optimization setup utilizes this summary to generate tailored recommendations. Through our experiments, we demonstrate the effectiveness of InteraRec in providing users with valuable and personalized offerings. Furthermore, we explore the integration of session-based recommendation systems into the InteraRec framework, aiming to enhance its overall performance. Finally, we curate a new dataset comprising of screenshots from product web pages on the Amazon website for the validation of the InteraRec framework. Detailed experiments demonstrate the efficacy of the InteraRec framework in delivering valuable and personalized recommendations tailored to individual user preferences.
Existing model-based interactive recommendation systems are trained by querying a world model to capture the user preference, but learning the world model from historical logged data will easily suffer from bias issues such as popularity bias and sampling bias. This is why some debiased methods have been proposed recently. However, two essential drawbacks still remain: 1) ignoring the dynamics of the time-varying popularity results in a false reweighting of items. 2) taking the unknown samples as negative samples in negative sampling results in the sampling bias. To overcome these two drawbacks, we develop a model called \textbf{i}dentifiable \textbf{D}ebiased \textbf{M}odel-based \textbf{I}nteractive \textbf{R}ecommendation (\textbf{iDMIR} in short). In iDMIR, for the first drawback, we devise a debiased causal world model based on the causal mechanism of the time-varying recommendation generation process with identification guarantees; for the second drawback, we devise a debiased contrastive policy, which coincides with the debiased contrastive learning and avoids sampling bias. Moreover, we demonstrate that the proposed method not only outperforms several latest interactive recommendation algorithms but also enjoys diverse recommendation performance.
Preference elicitation plays a central role in interactive recommender systems. Most preference elicitation approaches use either item queries that ask users to select preferred items from a slate, or attribute queries that ask them to express their preferences for item characteristics. Unfortunately, users often wish to describe their preferences using soft attributes for which no ground-truth semantics is given. Leveraging concept activation vectors for soft attribute semantics, we develop novel preference elicitation methods that can accommodate soft attributes and bring together both item and attribute-based preference elicitation. Our techniques query users using both items and soft attributes to update the recommender system's belief about their preferences to improve recommendation quality. We demonstrate the effectiveness of our methods vis-a-vis competing approaches on both synthetic and real-world datasets.
Rewards serve as a measure of user satisfaction and act as a limiting factor in interactive recommender systems. In this research, we focus on the problem of learning to reward (LTR), which is fundamental to reinforcement learning. Previous approaches either introduce additional procedures for learning to reward, thereby increasing the complexity of optimization, or assume that user-agent interactions provide perfect demonstrations, which is not feasible in practice. Ideally, we aim to employ a unified approach that optimizes both the reward and policy using compositional demonstrations. However, this requirement presents a challenge since rewards inherently quantify user feedback on-policy, while recommender agents approximate off-policy future cumulative valuation. To tackle this challenge, we propose a novel batch inverse reinforcement learning paradigm that achieves the desired properties. Our method utilizes discounted stationary distribution correction to combine LTR and recommender agent evaluation. To fulfill the compositional requirement, we incorporate the concept of pessimism through conservation. Specifically, we modify the vanilla correction using Bellman transformation and enforce KL regularization to constrain consecutive policy updates. We use two real-world datasets which represent two compositional coverage to conduct empirical studies, the results also show that the proposed method relatively improves both effectiveness (2.3\%) and efficiency (11.53\%)
Survivor bias in observational data leads the optimization of recommender systems towards local optima. Currently most solutions re-mines existing human-system collaboration patterns to maximize longer-term satisfaction by reinforcement learning. However, from the causal perspective, mitigating survivor effects requires answering a counterfactual problem, which is generally unidentifiable and inestimable. In this work, we propose a neural causal model to achieve counterfactual inference. Specifically, we first build a learnable structural causal model based on its available graphical representations which qualitatively characterizes the preference transitions. Mitigation of the survivor bias is achieved though counterfactual consistency. To identify the consistency, we use the Gumbel-max function as structural constrains. To estimate the consistency, we apply reinforcement optimizations, and use Gumbel-Softmax as a trade-off to get a differentiable function. Both theoretical and empirical studies demonstrate the effectiveness of our solution.
This paper studies the problem of learning interactive recommender systems from logged feedbacks without any exploration in online environments. We address the problem by proposing a general offline reinforcement learning framework for recommendation, which enables maximizing cumulative user rewards without online exploration. Specifically, we first introduce a probabilistic generative model for interactive recommendation, and then propose an effective inference algorithm for discrete and stochastic policy learning based on logged feedbacks. In order to perform offline learning more effectively, we propose five approaches to minimize the distribution mismatch between the logging policy and recommendation policy: support constraints, supervised regularization, policy constraints, dual constraints and reward extrapolation. We conduct extensive experiments on two public real-world datasets, demonstrating that the proposed methods can achieve superior performance over existing supervised learning and reinforcement learning methods for recommendation.
Interactive Recommender Systems (IRSs) have attracted a lot of attention, due to their ability to model interactive processes between users and recommender systems. Numerous approaches have adopted Reinforcement Learning (RL) algorithms, as these can directly maximize users' cumulative rewards. In IRS, researchers commonly utilize publicly available review datasets to compare and evaluate algorithms. However, user feedback provided in public datasets merely includes instant responses (e.g., a rating), with no inclusion of delayed responses (e.g., the dwell time and the lifetime value). Thus, the question remains whether these review datasets are an appropriate choice to evaluate the long-term effects of the IRS. In this work, we revisited experiments on IRS with review datasets and compared RL-based models with a simple reward model that greedily recommends the item with the highest one-step reward. Following extensive analysis, we can reveal three main findings: First, a simple greedy reward model consistently outperforms RL-based models in maximizing cumulative rewards. Second, applying higher weighting to long-term rewards leads to a degradation of recommendation performance. Third, user feedbacks have mere long-term effects on the benchmark datasets. Based on our findings, we conclude that a dataset has to be carefully verified and that a simple greedy baseline should be included for a proper evaluation of RL-based IRS approaches.
Offline reinforcement learning (RL), a technology that offline learns a policy from logged data without the need to interact with online environments, has become a favorable choice in decision-making processes like interactive recommendation. Offline RL faces the value overestimation problem. To address it, existing methods employ conservatism, e.g., by constraining the learned policy to be close to behavior policies or punishing the rarely visited state-action pairs. However, when applying such offline RL to recommendation, it will cause a severe Matthew effect, i.e., the rich get richer and the poor get poorer, by promoting popular items or categories while suppressing the less popular ones. It is a notorious issue that needs to be addressed in practical recommender systems. In this paper, we aim to alleviate the Matthew effect in offline RL-based recommendation. Through theoretical analyses, we find that the conservatism of existing methods fails in pursuing users' long-term satisfaction. It inspires us to add a penalty term to relax the pessimism on states with high entropy of the logging policy and indirectly penalizes actions leading to less diverse states. This leads to the main technical contribution of the work: Debiased model-based Offline RL (DORL) method. Experiments show that DORL not only captures user interests well but also alleviates the Matthew effect. The implementation is available via https://github.com/chongminggao/DORL-codes.
In dynamic interaction graphs, user-item interactions usually follow heterogeneous patterns, represented by different structural information, such as user-item co-occurrence, sequential information of user interactions and the transition probabilities of item pairs. However, the existing methods cannot simultaneously leverage all three structural information, resulting in suboptimal performance. To this end, we propose TriSIM4Rec, a triple structural information modeling method for accurate, explainable and interactive recommendation on dynamic interaction graphs. Specifically, TriSIM4Rec consists of 1) a dynamic ideal low-pass graph filter to dynamically mine co-occurrence information in user-item interactions, which is implemented by incremental singular value decomposition (SVD); 2) a parameter-free attention module to capture sequential information of user interactions effectively and efficiently; and 3) an item transition matrix to store the transition probabilities of item pairs. Then, we fuse the predictions from the triple structural information sources to obtain the final recommendation results. By analyzing the relationship between the SVD-based and the recently emerging graph signal processing (GSP)-based collaborative filtering methods, we find that the essence of SVD is an ideal low-pass graph filter, so that the interest vector space in TriSIM4Rec can be extended to achieve explainable and interactive recommendation, making it possible for users to actively break through the information cocoons. Experiments on six public datasets demonstrated the effectiveness of TriSIM4Rec in accuracy, explainability and interactivity.
Digital human recommendation system has been developed to help customers find their favorite products and is playing an active role in various recommendation contexts. How to timely catch and learn the dynamics of the preferences of the customers, while meeting their exact requirements, becomes crucial in the digital human recommendation domain. We design a novel practical digital human interactive recommendation agent framework based on Reinforcement Learning(RL) to improve the efficiency of the interactive recommendation decision-making by leveraging both the digital human features and the superior flexibility of RL. Our proposed framework learns through real-time interactions between the digital human and customers dynamically through the state-of-art RL algorithms, combined with multimodal embedding and graph embedding, to improve the accuracy of personalization and thus enable the digital human agent to timely catch the attention of the customer. Experiments on real business data demonstrate that our framework can provide better personalized customer engagement and better customer experiences.
Bandit algorithms have become a reference solution for interactive recommendation. However, as such algorithms directly interact with users for improved recommendations, serious privacy concerns have been raised regarding its practical use. In this work, we propose a differentially private linear contextual bandit algorithm, via a tree-based mechanism to add Laplace or Gaussian noise to model parameters. Our key insight is that as the model converges during online update, the global sensitivity of its parameters shrinks over time (thus named dynamic global sensitivity). Compared with existing solutions, our dynamic global sensitivity analysis allows us to inject less noise to obtain $(\epsilon, \delta)$-differential privacy with added regret caused by noise injection in $\tilde O(\log{T}\sqrt{T}/\epsilon)$. We provide a rigorous theoretical analysis over the amount of noise added via dynamic global sensitivity and the corresponding upper regret bound of our proposed algorithm. Experimental results on both synthetic and real-world datasets confirmed the algorithm's advantage against existing solutions.
Recommender systems deployed in real-world applications can have inherent exposure bias, which leads to the biased logged data plaguing the researchers. A fundamental way to address this thorny problem is to collect users' interactions on randomly expose items, i.e., the missing-at-random data. A few works have asked certain users to rate or select randomly recommended items, e.g., Yahoo!, Coat, and OpenBandit. However, these datasets are either too small in size or lack key information, such as unique user ID or the features of users/items. In this work, we present KuaiRand, an unbiased sequential recommendation dataset containing millions of intervened interactions on randomly exposed videos, collected from the video-sharing mobile App, Kuaishou. Different from existing datasets, KuaiRand records 12 kinds of user feedback signals (e.g., click, like, and view time) on randomly exposed videos inserted in the recommendation feeds in two weeks. To facilitate model learning, we further collect rich features of users and items as well as users' behavior history. By releasing this dataset, we enable the research of advanced debiasing large-scale recommendation scenarios for the first time. Also, with its distinctive features, KuaiRand can support various other research directions such as interactive recommendation, long sequential behavior modeling, and multi-task learning. The dataset and its news will be available at https://kuairand.com.
Recommender systems and search are both indispensable in facilitating personalization and ease of browsing in online fashion platforms. However, the two tools often operate independently, failing to combine the strengths of recommender systems to accurately capture user tastes with search systems' ability to process user queries. We propose a novel remedy to this problem by automatically recommending personalized fashion items based on a user-provided text request. Our proposed model, WhisperLite, uses contrastive learning to capture user intent from natural language text and improves the recommendation quality of fashion products. WhisperLite combines the strength of CLIP embeddings with additional neural network layers for personalization, and is trained using a composite loss function based on binary cross entropy and contrastive loss. The model demonstrates a significant improvement in offline recommendation retrieval metrics when tested on a real-world dataset collected from an online retail fashion store, as well as widely used open-source datasets in different e-commerce domains, such as restaurants, movies and TV shows, clothing and shoe reviews. We additionally conduct a user study that captures user judgements on the relevance of the model's recommended items, confirming the relevancy of WhisperLite's recommendations in an online setting.
Recommender systems are used in many different applications and contexts, however their main goal can always be summarised as "connecting relevant content to interested users". Personalized recommendation algorithms achieve this goal by first building a profile of the user, either implicitly or explicitly, and then matching items with this profile to find relevant content. The more interpretable the profile and this "matching function" are, the easier it is to provide users with accurate and intuitive explanations, and also to let them interact with the system. Indeed, for a user to see what the system has already learned about her interests is of key importance for her to provide feedback to the system and to guide it towards better understanding her preferences. To this end, we propose a linear collaborative filtering recommendation model that builds user profiles within the domain of item metadata, which is arguably the most interpretable domain for end users. Our method is hence inherently transparent and explainable. Moreover, since recommendations are computed as a linear function of item metadata and the interpretable user profile, our method seamlessly supports interactive recommendation. In other words, users can directly tweak the weights of the learned profile for more fine-grained browsing and discovery of content based on their current interests. We demonstrate the interactive aspect of this model in an online application for discovering cultural events in Belgium. Additionally, the performance of the model is evaluated with offline experiments, both static and with simulated feedback, and compared to several state-of-the-art and state-of-practice baselines.
While personalization increases the utility of recommender systems, it also brings the issue of filter bubbles. E.g., if the system keeps exposing and recommending the items that the user is interested in, it may also make the user feel bored and less satisfied. Existing work studies filter bubbles in static recommendation, where the effect of overexposure is hard to capture. In contrast, we believe it is more meaningful to study the issue in interactive recommendation and optimize long-term user satisfaction. Nevertheless, it is unrealistic to train the model online due to the high cost. As such, we have to leverage offline training data and disentangle the causal effect on user satisfaction. To achieve this goal, we propose a counterfactual interactive recommender system (CIRS) that augments offline reinforcement learning (offline RL) with causal inference. The basic idea is to first learn a causal user model on historical data to capture the overexposure effect of items on user satisfaction. It then uses the learned causal user model to help the planning of the RL policy. To conduct evaluation offline, we innovatively create an authentic RL environment (KuaiEnv) based on a real-world fully observed user rating dataset. The experiments show the effectiveness of CIRS in bursting filter bubbles and achieving long-term success in interactive recommendation. The implementation of CIRS is available via https://github.com/chongminggao/CIRS-codes.
Interactive recommendation is able to learn from the interactive processes between users and systems to confront the dynamic interests of users. Recent advances have convinced that the ability of reinforcement learning to handle the dynamic process can be effectively applied in the interactive recommendation. However, the sparsity of interactive data may hamper the performance of the system. We propose to train a Model-agnostic Counterfactual Synthesis Policy to generate counterfactual data and address the data sparsity problem by modelling from observation and counterfactual distribution. The proposed policy can identify and replace the trivial components for any state in the training process with other agents, which can be deployed in any RL-based algorithm. The experimental results demonstrate the effectiveness and generality of our proposed policy.
Adversarial attacks, e.g., adversarial perturbations of the input and adversarial samples, pose significant challenges to machine learning and deep learning techniques, including interactive recommendation systems. The latent embedding space of those techniques makes adversarial attacks difficult to detect at an early stage. Recent advance in causality shows that counterfactual can also be considered one of ways to generate the adversarial samples drawn from different distribution as the training samples. We propose to explore adversarial examples and attack agnostic detection on reinforcement learning-based interactive recommendation systems. We first craft different types of adversarial examples by adding perturbations to the input and intervening on the casual factors. Then, we augment recommendation systems by detecting potential attacks with a deep learning-based classifier based on the crafted data. Finally, we study the attack strength and frequency of adversarial examples and evaluate our model on standard datasets with multiple crafting methods. Our extensive experiments show that most adversarial attacks are effective, and both attack strength and attack frequency impact the attack performance. The strategically-timed attack achieves comparative attack performance with only 1/3 to 1/2 attack frequency. Besides, our black-box detector trained with one crafting method has the generalization ability over several other crafting methods.
Recently, interactive recommendation systems based on reinforcement learning have been attended by researchers due to the consider recommendation procedure as a dynamic process and update the recommendation model based on immediate user feedback, which is neglected in traditional methods. The existing works have two significant drawbacks. Firstly, inefficient ranking function to produce the Top-N recommendation list. Secondly, focusing on recommendation accuracy and inattention to other evaluation metrics such as diversity. This paper proposes a deep reinforcement learning based recommendation system by utilizing Actor-Critic architecture to model dynamic users' interaction with the recommender agent and maximize the expected long-term reward. Furthermore, we propose utilizing Spotify's ANNoy algorithm to find the most similar items to generated action by actor-network. After that, the Total Diversity Effect Ranking algorithm is used to generate the recommendations concerning relevancy and diversity. Moreover, we apply positional encoding to compute representations of the user's interaction sequence without using sequence-aligned recurrent neural networks. Extensive experiments on the MovieLens dataset demonstrate that our proposed model is able to generate a diverse while relevance recommendation list based on the user's preferences.