Search

Learning reinforcement learning (RL)-based recommenders from historical user-item interaction sequences is vital to generate high-reward recommendations and improve long-term cumulative benefits. However, existing RL recommendation methods encounter difficulties (i) to estimate the value functions for states which are not contained in the offline training data, and (ii) to learn effective state representations from user implicit feedback due to the lack of contrastive signals. In this work, we propose contrastive state augmentations (CSA) for the training of RL-based recommender systems. To tackle the first issue, we propose four state augmentation strategies to enlarge the state space of the offline data. The proposed method improves the generalization capability of the recommender by making the RL agent visit the local state regions and ensuring the learned value functions are similar between the original and augmented states. For the second issue, we propose introducing contrastive signals between augmented states and the state randomly sampled from other sessions to improve the state representation learning further. To verify the effectiveness of the proposed CSA, we conduct extensive experiments on two publicly accessible datasets and one dataset collected from a real-life e-commerce platform. We also conduct experiments on a simulated environment as the online evaluation setting. Experimental results demonstrate that CSA can effectively improve recommendation performance.

We consider the generalized successive overrelaxation (GSOR) method for solving a class of block three-by-three saddle-point problems. Based on the necessary and sufficient conditions for all roots of a real cubic polynomial to have modulus less than one, we derive convergence results under reasonable assumptions. We also analyze a class of block lower triangular preconditioners induced from GSOR and derive explicit and sharp spectral bounds for the preconditioned matrices. We report numerical experiments on test problems from the liquid crystal director model and the coupled Stokes-Darcy flow, demonstrating the usefulness of GSOR.

Learned recommender systems may inadvertently leak information about their training data, leading to privacy violations. We investigate privacy threats faced by recommender systems through the lens of membership inference. In such attacks, an adversary aims to infer whether a user's data is used to train the target recommender. To achieve this, previous work has used a shadow recommender to derive training data for the attack model, and then predicts the membership by calculating difference vectors between users' historical interactions and recommended items. State-of-the-art methods face two challenging problems: (1) training data for the attack model is biased due to the gap between shadow and target recommenders, and (2) hidden states in recommenders are not observational, resulting in inaccurate estimations of difference vectors. To address the above limitations, we propose a Debiasing Learning for Membership Inference Attacks against recommender systems (DL-MIA) framework that has four main components: (1) a difference vector generator, (2) a disentangled encoder, (3) a weight estimator, and (4) an attack model. To mitigate the gap between recommenders, a variational auto-encoder (VAE) based disentangled encoder is devised to identify recommender invariant and specific features. To reduce the estimation bias, we design a weight estimator, assigning a truth-level score for each difference vector to indicate estimation accuracy. We evaluate DL-MIA against both general recommenders and sequential recommenders on three real-world datasets. Experimental results show that DL-MIA effectively alleviates training and estimation biases simultaneously, and achieves state-of-the-art attack performance., Comment: Accepted by KDD 2022

The conjugate gradient (CG) method is a classic Krylov subspace method for solving symmetric positive definite linear systems. We introduce an analogous semi-conjugate gradient (SCG) method for unsymmetric positive definite linear systems. Unlike CG, SCG requires the solution of a lower triangular linear system to produce each semi-conjugate direction. We prove that SCG is theoretically equivalent to the full orthogonalization method (FOM), which is based on the Arnoldi process and converges in a finite number of steps. Because SCG's triangular system increases in size each iteration, we study a sliding window implementation (SWI) to improve efficiency, and show that the directions produced are still locally semi-conjugate. A counterexample illustrates that SWI is different from the direct incomplete orthogonalization method (DIOM), which is FOM with a sliding window. Numerical experiments from the convection-diffusion equation and other applications show that SCG is robust and that the sliding window implementation SWI allows SCG to solve large systems efficiently.

This paper presents a class of event-triggering rules for dynamical control systems with guaranteed positive minimum inter-event time (MIET). We first propose an event-based function design with guaranteed control performance under a clock-like variable for general nonlinear systems, and later specify them to general linear systems. Compared to the existing static and dynamic triggering mechanisms, the proposed triggering rules hold the robust global event-separation property, and can be easily implemented on practical digital platform. Namely, it is shown that the minimum inter-event time can be flexibly adapted to the various hardware limitations. Finally, several numerical simulations are given to illustrate the theoretical results., Comment: 8 pages, 7 figures, technical note

The Barzilai-Borwein (BB) method is a popular and efficient tool for solving large-scale unconstrained optimization problems. Its search direction is the same as for the steepest descent (Cauchy) method, but its stepsize rule is different. Owing to this, it converges much faster than the Cauchy method. A feature of the BB method is that it may generate too long steps, which throw the iterates too far away from the solution. Moreover, it may not converge, even when the objective function is strongly convex. In this paper, a stabilization technique is introduced. It consists in bounding the distance between each pair of successive iterates, which often allows for decreasing the number of BB iterations. When the BB method does not converge, our simple modification of this method makes it convergent. Under suitable assumptions, we prove its global convergence, despite the fact that no line search is involved, and only gradient values are used. Since the number of stabilization steps is proved to be finite, the stabilized version inherits the fast local convergence of the BB method. The presented results of extensive numerical experiments show that our stabilization technique often allows the BB method to solve problems in a fewer iterations, or even to solve problems where the latter fails.