Reinforcement learning (RL) has recently been introduced to interactive recommender systems (IRS) because of its nature of learning from dynamic interactions and planning for long-run performance. As IRS is always with thousands of items to recommend (i.e., thousands of actions), most existing RL-based methods, however…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,695 papers · 148 categories
Trend · papers per month
48 results for “actionable recommendations”
In many online applications interactions between a user and a web-service are organized in a sequential way, e.g., user browsing an e-commerce website. In this setting, recommendation system acts throughout user navigation by showing items. Previous works have addressed this recommendation setup through the task of pre…
PSI-LinUCB improves scalability for large recommender systems.
problem Efficiently training and inferring for large action spaces in recommender systems.
method Represent inverse design matrix as diagonal + low-rank correction, derive stable rank-1 and batched updates, use projector-splitting integrator.
result Demonstrated effectiveness on recommender system datasets, achieving scalable training and inference.
Interpretable explanations for recommender systems and other machine learning models are crucial to gain user trust. Prior works that have focused on paths connecting users and items in a heterogeneous network have several limitations, such as discovering relationships rather than true explanations, or disregarding oth…
Deviation-based learning improves recommender systems by abstaining from recommending choices users might follow.
problem Recommender systems learn from user choices but can stall if users blindly follow recommendations.
method The recommender learns user knowledge by observing choices, abstaining from recommending a choice when multiple alternatives produce similar payoffs.
result Learning rate and social welfare improve when the recommender abstains from recommending certain choices.
Recourse explanations can become invalid if collective actions change statistical data.
problem Recourse explanations may become invalid due to collective behavior changing data statistics.
method Formal characterization of conditions under which recourse explanations remain valid under performativity.
result Recourse actions may become invalid if they are influenced by or intervene on non-causal variables.
BLOB combines organic and bandit signals for better user interest estimation.
problem Combining organic and bandit signals for improved user interest estimation.
method Bayesian Latent Organic Bandit (BLOB) model using variational auto-encoders and local re-parametrization.
result BLOB outperforms organic and bandit-based methods in both organic and bandit-rich environments.
Industrial recommender systems deal with extremely large action spaces -- many millions of items to recommend. Moreover, they need to serve billions of users, who are unique at any point in time, making a complex user state space. Luckily, huge quantities of logged implicit feedback (e.g., user clicks, dwell time) are …
CFRecs uses counterfactual reasoning to improve graph-based recommendations in real estate.
problem Improving model interpretability and actionable insights in graph-based recommender systems.
method A two-stage architecture combining GNN and Graph-VAE to propose minimal yet impactful changes in graph structure and node attributes.
result Demonstrates effectiveness in delivering actionable recommendations for home buyers and sellers.
Improves algorithmic recourse to guide towards both acceptance and improvement.
problem Algorithmic recourse recommendations may not lead to improvement.
method Improvement-Focused Causal Recourse (ICR) requires recommendations to guide towards improvement and leverages causal knowledge to design accurate decision systems.
result ICR guides towards both acceptance and improvement given correct causal knowledge.
There are three quite distinct ways to train a machine learning model on recommender system logs. The first method is to model the reward prediction for each possible recommendation to the user, at the scoring time the best recommendation is found by computing an argmax over the personalized recommendations. This metho…
Email has remained a principal form of communication among people, both in enterprise and social settings. With a deluge of emails crowding our mailboxes daily, there is a dire need of smart email systems that can recover important emails and make personalized recommendations. In this work, we study the problem of pred…
Unified approach for conversational recommendation by integrating attributes and items.
problem Cold-start users' real-time personalization in online recommendation.
method Seamlessly unifies attributes and items in Thompson Sampling framework for interactive decision-making.
result Conversational Thompson Sampling (ConTS) outperforms existing methods in success rate and conversation turns.
Develops a two-level monotonic multistage recommender system for better user-specific prediction.
problem Leveraging user-item-stage dependencies in a monotonic chain of events for enhanced prediction accuracy.
method A multistage recommender system with a two-level monotonic property, using a large-margin classifier based on a nonnegative additive latent factor model.
result The proposed method outperforms existing methods in simulations and an article sharing dataset.
New probabilistic approaches offer recourse recommendations even when causal models are imperfect.
problem Limited causal knowledge makes guaranteeing algorithmic recourse impossible.
method Two probabilistic approaches: Bayesian model averaging and average effect computation.
result Probabilistic approaches lead to more reliable recourse recommendations.
Proposes using frequent sequences to improve sequential recommendation models.
problem Combining user history and recent actions for personalized recommendations.
method Uses frequent sequences to identify relevant parts of user history, embedding items based on preferences and dynamics in a unified metric model.
result Outperforms state-of-the-art methods, especially on sparse datasets.
In recent years, content recommendation systems in large websites (or \emph{content providers}) capture an increased focus. While the type of content varies, e.g.\ movies, articles, music, advertisements, etc., the high level problem remains the same. Based on knowledge obtained so far on the user, recommend the most d…
PriRec preserves privacy in POI recommendation by keeping data and models on users' devices.
problem Privacy concerns in centralized POI recommendation models.
method Local differential privacy for sensitive data, secure decentralized gradient descent for linear models, secure aggregation for feature interactions.
result PriRec achieves comparable or better recommendation accuracy than FM while protecting user privacy.
We propose a method for building an interpretable recommender system for personalizing online content and promotions. Historical data available for the system consists of customer features, provided content (promotions), and user responses. Unlike in a standard multi-class classification setting, misclassification cost…
Adobe research tackles strategic recommendations using reinforcement learning.
problem Optimizing user interactions for long-term objectives in various use-cases.
method Reinforcement learning applied to modeling user behavior and decision-making.
result Practical solutions implemented for various use-cases, addressing fundamental challenges.
Scalable model for slate recommendation learns reward probabilities.
problem Scalable personalized slate recommendation in large action spaces.
method Probabilistic Rank and Reward (PRR) model combining reward, interaction, and rank.
result PRR outperforms existing methods and is scalable to large action spaces.
PinnerSage creates multi-modal user embeddings for better Pinterest recommendations.
problem Single high-dimensional embeddings fail to fully understand user interests.
method Hierarchical clustering and Medoids to summarize user actions into coherent clusters.
result PinnerSage outperforms single embedding methods in personalized recommendations.
Most practical recommender systems focus on estimating immediate user engagement without considering the long-term effects of recommendations on user behavior. Reinforcement learning (RL) methods offer the potential to optimize recommendations for long-term user engagement. However, since users are often presented with…
Proposes minimal interventions over counterfactual explanations for algorithmic recourse.
problem Lack of actionable recommendations for algorithmic recourse.
method Causal reasoning to shift focus from explanations to recommendations.
result Minimal interventions provide more actionable recommendations for recourse.
Decision makers, such as doctors and judges, make crucial decisions such as recommending treatments to patients, and granting bails to defendants on a daily basis. Such decisions typically involve weighting the potential benefits of taking an action against the costs involved. In this work, we aim to automate this task…
Study designs logging policies to minimize off-policy evaluation error.
problem Minimizing OPE error with logging policies for target policies.
method Characterizes reward-coverage tradeoff, proposes a unifying framework, derives optimal policies.
result Provides actionable guidance for firms choosing recommendation systems.
A new algorithm improves recommendation systems by considering repeated exposure to actions.
problem Improving recommendation systems by accounting for human memory decay.
method Introducing Weighted Tallying Bandits (WTB) and studying them under Repeated Exposure Optimality (REO).
result A simple modification of the successive elimination algorithm achieves nearly optimal complete policy regret.
In the context of tree-search stochastic planning algorithms where a generative model is available, we consider on-line planning algorithms building trees in order to recommend an action. We investigate the question of avoiding re-planning in subsequent decision steps by directly using sub-trees as action recommender. …
State of the art music recommender systems mainly rely on either matrix factorization-based collaborative filtering approaches or deep learning architectures. Deep learning models usually use metadata for content-based filtering or predict the next user interaction by learning from temporal sequences of user actions. D…
Uplifting Banditsstat.ML
UCB algorithms estimate uplifts in multi-variable reward systems.
problem Marketing campaigns and recommender systems with multiple outcome variables.
method UCB-style algorithms for estimating uplifts over a baseline.
result Sublinear regret bounds for multiple problem variants.
The problem of session-based recommendation aims to predict user actions based on anonymous sessions. Previous methods model a session as a sequence and estimate user representations besides item representations to make recommendations. Though achieved promising results, they are insufficient to obtain accurate user ve…
TOFU-POV tackles partially observed linear bandits, achieving sublinear regret with low-dimensional action vectors.
problem Stochastic linear bandits with partially observed actions in settings like recommendation and healthcare.
method TOFU-POV estimates latent action subspace, imputes missing actions, and runs OFUL in low-dimensional coordinates.
result TOFU-POV achieves regret scaling with intrinsic subspace dimension, improving upon natural baselines.
We achieve a finite regret bound of O(dlogd) for online inverse linear optimization with M-convex action sets.
problem Online inverse linear optimization with M-convex action sets.
method Combining structural characterization of optimal solutions on M-convex sets with geometric volume argument.
result Finite regret bound of O(dlogd) for online inverse linear optimization with M-convex action sets.
BanditLP optimizes personalized recommendations for large-scale systems.
problem Optimizing personalized recommendations for large-scale systems with constraints.
method Unified neural Thompson Sampling for learning and large-scale linear programming for action selection.
result Consistent gains over strong baselines in experiments and business win in LinkedIn's email marketing system.
FedRule uses graph neural networks to recommend rules for smart homes without centralizing data.
problem Manual rule setup for smart devices is inefficient and privacy-compromising.
method FedRule constructs user-specific graphs for rule recommendation, using federated learning to protect privacy.
result FedRule achieves comparable performance to centralized methods and outperforms others.
The paper uses machine learning to find causal rules from business process logs.
problem Discovering causal relationships in business process logs.
method Action rule mining followed by causal machine learning (uplift trees).
result Identifies treatments with high causal effect on outcomes.
In many practical problems, a learning agent may want to learn the best action in hindsight without ever taking a bad action, which is significantly worse than the default production action. In general, this is impossible because the agent has to explore unknown actions, some of which can be bad, to learn better action…
Proposes a new framework for resource-limited recommendation.
problem Resource constraints affect user choices in recommendation tasks.
method Interest-behavior multiplicative network with MRRNNs and resource-limited branch.
result Framework effectively predicts user interactions considering resource limitations.
Contextual bandit methods fail with deficient support data.
problem Learning from support-deficient data in contextual bandits.
method Three approaches to IPS-based learning: action space restriction, reward extrapolation, and policy space restriction.
result Systematic analysis and empirical evaluation of approaches to IPS-based learning.
New estimator GMIPS reduces variance in ranking policy evaluation.
problem High variance in off-policy evaluation for ranking policies.
method GMIPS estimator with user behavior model on ranking embedding spaces.
result GMIPS achieves lowest MSE and balances bias-variance trade-off.
While a user's preference is directly reflected in the interactive choice process between her and the recommender, this wealth of information was not fully exploited for learning recommender models. In particular, existing collaborative filtering (CF) approaches take into account only the binary events of user actions …
In most real-world settings such as recommender systems, finance, and healthcare, collecting useful information is costly and requires an active choice on the part of the decision maker. The decision-maker needs to learn simultaneously what observations to make and what actions to take. This paper incorporates the info…
CASP selects reliable policies for two-stage recommender systems by considering both value and support.
problem The selection of a generator in two-stage recommender systems affects both the policy value and the data support used to estimate it.
method CASP combines doubly robust value estimation with a support-burden penalty.
result CASP selects lower-burden policies when estimated value and support credibility are in tension.
In sponsored search, keyword recommendations help advertisers to achieve much better performance within limited budget. Many works have been done to mine numerous candidate keywords from search logs or landing pages. However, the strategy to select from given candidates remains to be improved. The existing relevance-ba…
A new MDP with Bandits approach for sequential decision making in linear-flow scenarios.
problem Sequential decision making with limited feedback in a linear-flow context.
method Formulated as an MDP with Bandits, using Thompson sampling for action selection and exact dynamic programming for allocation.
result The proposed MDP with Bandits algorithm outperforms other methods in sequential decision making.
Solves action selection for large spaces in RL, achieving near-optimal performance.
problem Selecting a small, representative subset of actions from a large, shared action space.
method Extends meta-bandit approach to MDPs, using a relaxed sub-Gaussian process model.
result Achieves performance comparable to full action space, with theoretical guarantees.
Study shows how repetition affects learning in bandit settings, providing algorithms with sublinear regret.
problem Effect of persistence of engagement on learning in stochastic multi-armed bandit settings.
method Novel algorithms that achieve sublinear regret under temporal constraints.
result Additive effect of priming on regret upper bound, matching popular algorithms in absence of priming.
A Deep Learning Method for Predicting Mergers and Acquisitions: Temporal Dynamic Industry Networksq-fin.ST
Deep learning predicts M&A events in industry networks.
problem Predicting M&A behaviors in competitive industries with complex interdependencies.
method Temporal Dynamic Industry Network (TDIN) model using temporal point processes and deep learning.
result Effective M&A event prediction and actionable recommendations.