Dual-Phase Accelerated Prompt Optimization

Gradient-free prompt optimization methods have made significant strides in enhancing the performance of closed-source Large Language Models (LLMs) across a wide range of tasks. However, existing approaches make light of the importance of high-quality prompt initialization and the identification of effective optimization directions, thus resulting in substantial optimization steps to obtain satisfactory performance. In this light, we aim to accelerate prompt optimization process to tackle the challenge of low convergence rate. We propose a dual-phase approach which starts with generating high-quality initial prompts by adopting a well-designed meta-instruction to delve into task-specific information, and iteratively optimize the prompts at the sentence level, leveraging previous tuning experience to expand prompt candidates and accept effective ones. Extensive experiments on eight datasets demonstrate the effectiveness of our proposed method, achieving a consistent accuracy gain over baselines with less than five optimization steps.

Treatment Effect Estimation for User Interest Exploration on Recommender Systems

Recommender systems learn personalized user preferences from user feedback like clicks. However, user feedback is usually biased towards partially observed interests, leaving many users' hidden interests unexplored. Existing approaches typically mitigate the bias, increase recommendation diversity, or use bandit algorithms to balance exploration-exploitation trade-offs. Nevertheless, they fail to consider the potential rewards of recommending different categories of items and lack the global scheduling of allocating top-N recommendations to categories, leading to suboptimal exploration. In this work, we propose an Uplift model-based Recommender (UpliftRec) framework, which regards top-N recommendation as a treatment optimization problem. UpliftRec estimates the treatment effects, i.e., the click-through rate (CTR) under different category exposure ratios, by using observational user feedback. UpliftRec calculates group-level treatment effects to discover users' hidden interests with high CTR rewards and leverages inverse propensity weighting to alleviate confounder bias. Thereafter, UpliftRec adopts a dynamic programming method to calculate the optimal treatment for overall CTR maximization. We implement UpliftRec on different backend models and conduct extensive experiments on three datasets. The empirical results validate the effectiveness of UpliftRec in discovering users' hidden interests while achieving superior recommendation accuracy.

How Do Recommendation Models Amplify Popularity Bias? An Analysis from the Spectral Perspective

Recommendation Systems (RS) are often plagued by popularity bias. Specifically,when recommendation models are trained on long-tailed datasets, they not only inherit this bias but often exacerbate it. This effect undermines both the precision and fairness of RS and catalyzes the so-called Matthew Effect. Despite the widely recognition of this issue, the fundamental causes remain largely elusive. In our research, we delve deeply into popularity bias amplification. Our comprehensive theoretical and empirical investigations lead to two core insights: 1) Item popularity is memorized in the principal singular vector of the score matrix predicted by the recommendation model; 2) The dimension collapse phenomenon amplifies the impact of principal singular vector on model predictions, intensifying the popularity bias. Based on these insights, we propose a novel method to mitigate this bias by imposing penalties on the magnitude of the principal singular value. Considering the heavy computational burden in directly evaluating the gradient of the principal singular value, we develop an efficient algorithm that harnesses the inherent properties of the singular vector. Extensive experiments across seven real-world datasets and three testing scenarios have been conducted to validate the superiority of our method.

Leave No Patient Behind: Enhancing Medication Recommendation for Rare Disease Patients

Medication recommendation systems have gained significant attention in healthcare as a means of providing tailored and effective drug combinations based on patients' clinical information. However, existing approaches often suffer from fairness issues, as recommendations tend to be more accurate for patients with common diseases compared to those with rare conditions. In this paper, we propose a novel model called Robust and Accurate REcommendations for Medication (RAREMed), which leverages the pretrain-finetune learning paradigm to enhance accuracy for rare diseases. RAREMed employs a transformer encoder with a unified input sequence approach to capture complex relationships among disease and procedure codes. Additionally, it introduces two self-supervised pre-training tasks, namely Sequence Matching Prediction (SMP) and Self Reconstruction (SR), to learn specialized medication needs and interrelations among clinical codes. Experimental results on two real-world datasets demonstrate that RAREMed provides accurate drug sets for both rare and common disease patients, thereby mitigating unfairness in medication recommendation systems.

Enhancing Long-Term Recommendation with Bi-level Learnable Large Language Model Planning

Traditional recommendation setting tends to excessively cater to users' immediate interests and neglect their long-term engagement. To address it, it is crucial to incorporate planning capabilities into the recommendation decision-making process to develop policies that take into account both immediate interests and long-term engagement. Despite Reinforcement Learning (RL) can learn planning capacity by maximizing cumulative reward, the scarcity of recommendation data presents challenges such as instability and susceptibility to overfitting when training RL models from scratch. In this context, we propose to leverage the remarkable planning capabilities over sparse data of Large Language Models (LLMs) for long-term recommendation. The key lies in enabling a language model to understand and apply task-solving principles effectively in personalized recommendation scenarios, as the model's pre-training may not naturally encompass these principles, necessitating the need to inspire or teach the model. To achieve this, we propose a Bi-level Learnable LLM Planner framework, which combines macro-learning and micro-learning through a hierarchical mechanism. The framework includes a Planner and Reflector for acquiring high-level guiding principles and an Actor-Critic component for planning personalization. Extensive experiments validate the superiority of the framework in learning to plan for long-term recommendations.

EasyRL4Rec: A User-Friendly Code Library for Reinforcement Learning Based Recommender Systems

Reinforcement Learning (RL)-Based Recommender Systems (RSs) are increasingly recognized for their ability to improve long-term user engagement. Yet, the field grapples with challenges such as the absence of accessible frameworks, inconsistent evaluation standards, and the complexity of replicating prior work. Addressing these obstacles, we present EasyRL4Rec, a user-friendly and efficient library tailored for RL-based RSs. EasyRL4Rec features lightweight, diverse RL environments built on five widely-used public datasets, and is equipped with comprehensive core modules that offer rich options to ease the development of models. It establishes consistent evaluation criteria with a focus on long-term impacts and introduces customized solutions for state modeling and action representation tailored to recommender systems. Additionally, we share valuable insights gained from extensive experiments with current methods. EasyRL4Rec aims to facilitate the model development and experimental process in the domain of RL-based RSs. The library is openly accessible at https://github.com/chongminggao/EasyRL4Rec.

RecAD: Towards A Unified Library for Recommender Attack and Defense

In recent years, recommender systems have become a ubiquitous part of our daily lives, while they suffer from a high risk of being attacked due to the growing commercial and social values. Despite significant research progress in recommender attack and defense, there is a lack of a widely-recognized benchmarking standard in the field, leading to unfair performance comparison and limited credibility of experiments. To address this, we propose RecAD, a unified library aiming at establishing an open benchmark for recommender attack and defense. RecAD takes an initial step to set up a unified benchmarking pipeline for reproducible research by integrating diverse datasets, standard source codes, hyper-parameter settings, running logs, attack knowledge, attack budget, and evaluation results. The benchmark is designed to be comprehensive and sustainable, covering both attack, defense, and evaluation tasks, enabling more researchers to easily follow and contribute to this promising field. RecAD will drive more solid and reproducible research on recommender systems attack and defense, reduce the redundant efforts of researchers, and ultimately increase the credibility and practical value of recommender attack and defense. The project is released at https://github.com/gusye1234/recad.

Alleviating Matthew Effect of Offline Reinforcement Learning in Interactive Recommendation

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.

Embracing Uncertainty: Adaptive Vague Preference Policy Learning for Multi-round Conversational Recommendation

Conversational recommendation systems (CRS) effectively address information asymmetry by dynamically eliciting user preferences through multi-turn interactions. Existing CRS widely assumes that users have clear preferences. Under this assumption, the agent will completely trust the user feedback and treat the accepted or rejected signals as strong indicators to filter items and reduce the candidate space, which may lead to the problem of over-filtering. However, in reality, users' preferences are often vague and volatile, with uncertainty about their desires and changing decisions during interactions. To address this issue, we introduce a novel scenario called Vague Preference Multi-round Conversational Recommendation (VPMCR), which considers users' vague and volatile preferences in CRS.VPMCR employs a soft estimation mechanism to assign a non-zero confidence score for all candidate items to be displayed, naturally avoiding the over-filtering problem. In the VPMCR setting, we introduce an solution called Adaptive Vague Preference Policy Learning (AVPPL), which consists of two main components: Uncertainty-aware Soft Estimation (USE) and Uncertainty-aware Policy Learning (UPL). USE estimates the uncertainty of users' vague feedback and captures their dynamic preferences using a choice-based preferences extraction module and a time-aware decaying strategy. UPL leverages the preference distribution estimated by USE to guide the conversation and adapt to changes in users' preferences to make recommendations or ask for attributes. Our extensive experiments demonstrate the effectiveness of our method in the VPMCR scenario, highlighting its potential for practical applications and improving the overall performance and applicability of CRS in real-world settings, particularly for users with vague or dynamic preferences.

On the Theories Behind Hard Negative Sampling for Recommendation

Negative sampling has been heavily used to train recommender models on large-scale data, wherein sampling hard examples usually not only accelerates the convergence but also improves the model accuracy. Nevertheless, the reasons for the effectiveness of Hard Negative Sampling (HNS) have not been revealed yet. In this work, we fill the research gap by conducting thorough theoretical analyses on HNS. Firstly, we prove that employing HNS on the Bayesian Personalized Ranking (BPR) learner is equivalent to optimizing One-way Partial AUC (OPAUC). Concretely, the BPR equipped with Dynamic Negative Sampling (DNS) is an exact estimator, while with softmax-based sampling is a soft estimator. Secondly, we prove that OPAUC has a stronger connection with Top-K evaluation metrics than AUC and verify it with simulation experiments. These analyses establish the theoretical foundation of HNS in optimizing Top-K recommendation performance for the first time. On these bases, we offer two insightful guidelines for effective usage of HNS: 1) the sampling hardness should be controllable, e.g., via pre-defined hyper-parameters, to adapt to different Top-K metrics and datasets; 2) the smaller the $K$ we emphasize in Top-K evaluation metrics, the harder the negative samples we should draw. Extensive experiments on three real-world benchmarks verify the two guidelines.