Online dating is one of the surest and quickest ways to meet someone. The possibilities of finding what you're looking for are as wide as the internet search. Sometimes you find who you want, but for more and more women, swiping left has exposed them to untold dangers. Increasingly, online dating has become a space where women are being exposed to sexual violence and abuse. This week on Now You Know we talk to Jackie Cruz, a sexual violence researcher, about how women can stay safe on dating apps.

The authors motivate the proposed model with the setting in which items have "true" but unobserved labels/ratings and the observed labels/ratings given by evaluators are potentially incorrect. This differs from the very common problem in recommendation systems or collaborative filtering where evaluators provide their subjective ratings but there is not assumed to be any "true" rating (e.g., users of Netflix giving 1-5 star ratings to movies). This seems like a common but underexplored setting that is worthy of further study within machine learning. The authors are also right to highlight interpretability as a desired aspect of any machine learning solution that may yield post-hoc insights into common human biases and thus suggest corrective measures. This paper does a good job of motivating the proposed model and situating it within the crowdsourcing and human annotation literature.

First of all, the problem considered in this paper is interesting and useful to some potential applications that require the true rating matrix not influenced by any recommender systems. However, the inference of the true rating matrix from the observed one is an ill-posed problem, which need the "strong" (somewhat unrealistic) assumptions. The questions about the assumptions are summarized as follows: 1. Assumption 1 is quite restricted in the sense that the popular recommendation algorithms (e.x. Bayesian matrix factorization) cannot be properly expressed in Eq. (2). If the real-world RS makes use of a complex recommendation algorithm that is not covered by the Assumption 1, it is hard to validate the quality of the true rating matrix extracted by the proposed algorithm. I think that this is also non-realistic situation.

The paper explores an important topic – adversarial machine learning. While the paper contributes interesting results, it seems slightly lacking in novelty/depth. In general, the paper is well presented. Both the attack models and strategies are clearly derived and explained. It is indeed important to have this kind of analysis to fully understand the vulnerability of collaborative filtering schemes.

The authors do a good job of presenting the high-level ideas behind their contribution and presenting the relevant literature in context. The actual contribution is quite technical in nature, but a good amount of effort is taken to walk the reader through it. The authors might also look into approaches like SLIM (Ning and Karypis), which also approach matrix completion tasks using (fairly simple) models that overcome the low-rank assumption of typical matrix completion approaches. Although the paper promises to recover matrix data generated by a quite general class of functions, I struggled to understand which of the operating assumptions (section 2) are actually realistic. In particular, assumption (e) (each entry is observed independently) is certainly violated in the netflix and movielens datasets where the "missing at random" assumption does not hold (as would be the case in any dataset where users self-select what to evaluate; see papers on the "missing not at random" assumption).

User preferences for items can be inferred from either explicit feedback, such as item ratings, or implicit feedback, such as rental histories. Research in collaborative filtering has concentrated on explicit feedback, resulting in the development of accurate and scalable models. However, since explicit feedback is often difficult to collect it is important to develop effective models that take advantage of the more widely available implicit feedback. We introduce a probabilistic approach to collaborative filtering with implicit feedback based on modelling the user's item selection process. In the interests of scalability, we restrict our attention to tree-structured distributions over items and develop a principled and efficient algorithm for learning item trees from data.

The past decade has witnessed the flourishing of a new profession as media content creators, who rely on revenue streams from online content recommendation platforms. The reward mechanism employed by these platforms creates a competitive environment among creators which affects their production choices and, consequently, content distribution and system welfare. It is thus crucial to design the platform's reward mechanism in order to steer the creators' competition towards a desirable welfare outcome in the long run. This work makes two major contributions in this regard: first, we uncover a fundamental limit about a class of widely adopted mechanisms, coined \emph{Merit-based Monotone Mechanisms}, by showing that they inevitably lead to a constant fraction loss of the optimal welfare. To circumvent this limitation, we introduce \emph{Backward Rewarding Mechanisms} (BRMs) and show that the competition game resultant from BRMs possesses a potential game structure. BRMs thus naturally induce strategic creators' collective behaviors towards optimizing the potential function, which can be designed to match any given welfare metric.

The state-of-the-art recommendation systems have shifted the attention to efficient recommendation, e.g., on-device recommendation, under memory constraints. To this end, the existing methods either focused on the lightweight embeddings for both users and items, or involved on-device systems enjoying the compact embeddings to enhance reusability and reduces space complexity. However, they focus solely on the coarse granularity of embedding, while overlook the fine-grained semantic nuances, to adversarially downgrade the efficacy of meta-embeddings in capturing the intricate relationship over both user and item, consequently resulting into the suboptimal recommendations. In this paper, we aim to study how the meta-embedding can efficiently learn varied grained semantics, together with how the fine-grained meta-embedding can strengthen the representation of coarse-grained meta-embedding. To answer these questions, we develop a novel graph neural networks (GNNs) based recommender where each user and item serves as the node, linked directly to coarse-grained virtual nodes and indirectly to fine-grained virtual nodes, ensuring different grained semantic learning, while disclosing: 1) In contrast to coarse-grained semantics, fine-grained semantics are well captured through sparse meta-embeddings, which adaptively 2) balance the embedding uniqueness and memory constraint. Additionally, the initialization method come up upon SparsePCA, along with a soft thresholding activation function to render the sparseness of the meta-embeddings. We propose a weight bridging update strategy that focuses on matching each coarse-grained meta-embedding with several fine-grained meta-embeddings based on the users/items' semantics. Extensive experiments substantiate our method's superiority over existing baselines. Our code is available at https://github.com/htyjers/C2F-MetaEmbed.

Graph-based Collaborative Filtering (GCF) is widely used in personalized recommendation systems. However, GCF suffers from a fundamental problem where features tend to occupy the embedding space inefficiently (by spanning only a low-dimensional subspace). Such an effect is characterized in GCF by the embedding space being dominated by a few of popular items with the user embeddings highly concentrated around them. This enhances the so-called Matthew effect of the popularity bias where popular items are highly recommend whereas remaining items are ignored. In this paper, we analyze the above effect in GCF and reveal that the simplified graph convolution operation (typically used in GCF) shrinks the singular space of the feature matrix.

Graph contrastive learning (GCL) has emerged as a potent technology for numerous graph learning tasks. It has been successfully applied to real-world recommender systems, where the contrastive loss and the downstream recommendation objectives are always combined to form the overall objective function. Such a strategy is inconsistent with the original GCL paradigm, where graph embeddings are pre-trained without involving downstream training objectives. In this paper, we innovatively propose a prompt-enhanced framework for GCL-based recommender systems, namely CPTPP, which can fully leverage the advantages of the original GCL protocol through prompt tuning. Specifically, we first summarise user profiles in graph recommender systems to automatically generate personalized user prompts.