Popularity bias is a pervasive problem in recommender systems, where recommendations disproportionately favor popular items. This not only results in "rich-get-richer" dynamics and a homogenization of visible content, but can also lead to misalignment of recommendations with individual users' preferences for popular or niche content. This work studies popularity bias through the lens of user-recommender alignment. To this end, we introduce Popularity Quantile Calibration, a measurement framework that quantifies misalignment between a user's historical popularity preference and the popularity of their recommendations. Building on this notion of popularity alignment, we propose SPREE, an inference-time mitigation method for sequential recommenders based on activation steering. SPREE identifies a popularity direction in representation space and adaptively steers model activations based on an estimate of each user's personal popularity bias, allowing both the direction and magnitude of steering to vary across users. Unlike global debiasing approaches, SPREE explicitly targets alignment rather than uniformly reducing popularity. Experiments across multiple datasets show that SPREE consi
Collaborative Filtering (CF) typically suffers from the significant challenge of popularity bias due to the uneven distribution of items in real-world datasets. This bias leads to a significant accuracy gap between popular and unpopular items. It not only hinders accurate user preference understanding but also exacerbates the Matthew effect in recommendation systems. To alleviate popularity bias, existing efforts focus on emphasizing unpopular items or separating the correlation between item representations and their popularity. Despite the effectiveness, existing works still face two persistent challenges: (1) how to extract common supervision signals from popular items to improve the unpopular item representations, and (2) how to alleviate the representation separation caused by popularity bias. In this work, we conduct an empirical analysis of popularity bias and propose Popularity-Aware Alignment and Contrast (PAAC) to address two challenges. Specifically, we use the common supervisory signals modeled in popular item representations and propose a novel popularity-aware supervised alignment module to learn unpopular item representations. Additionally, we suggest re-weighting the
We study popular matchings in three classical settings: the house allocation problem, the marriage problem, and the roommates problem. In the popular matching problem, (a subset of) the vertices in a graph have preference orderings over their potential matches. A matching is popular if it gets a plurality of votes in a pairwise election against any other matching. Unfortunately, popular matchings typically do not exist. So we study a natural relaxation, namely popular winning sets which are a set of matchings that collectively get a plurality of votes in a pairwise election against any other matching. The $\textit{popular dimension}$ is the minimum cardinality of a popular winning set, in the worst case over the problem class. We prove that the popular dimension is exactly $2$ in the house allocation problem, even if the voters are weighted and ties are allowed in their preference lists. For the marriage problem and the roommates problem, we prove that the popular dimension is between $2$ and $3$, when the agents are weighted and/or their preferences orderings allow ties. In the special case where the agents are unweighted and have strict preference orderings, the popular dimension
Point-of-interest (POI) recommender systems help users discover relevant locations, but their effectiveness is often compromised by popularity bias, which disadvantages less popular, yet potentially meaningful places. This paper addresses this challenge by evaluating the effectiveness of context-aware models and calibrated popularity techniques as strategies for mitigating popularity bias. Using four real-world POI datasets (Brightkite, Foursquare, Gowalla, and Yelp), we analyze the individual and combined effects of these approaches on recommendation accuracy and popularity bias. Our results reveal that context-aware models cannot be considered a uniform solution, as the models studied exhibit divergent impacts on accuracy and bias. In contrast, calibration techniques can effectively align recommendation popularity with user preferences, provided there is a careful balance between accuracy and bias mitigation. Notably, the combination of calibration and context-awareness yields recommendations that balance accuracy and close alignment with the users' popularity profiles, i.e., popularity calibration.
Let $G = (A \cup B,E)$ be a bipartite graph where the set $A$ consists of agents or main players and the set $B$ consists of jobs or secondary players. Every vertex has a strict ranking of its neighbors. A matching $M$ is popular if for any matching $N$, the number of vertices that prefer $M$ to $N$ is at least the number that prefer $N$ to $M$. Popular matchings always exist in $G$ since every stable matching is popular. A matching $M$ is $A$-popular if for any matching $N$, the number of agents (i.e., vertices in $A$) that prefer $M$ to $N$ is at least the number of agents that prefer $N$ to $M$. Unlike popular matchings, $A$-popular matchings need not exist in a given instance $G$ and there is a simple linear time algorithm to decide if $G$ admits an $A$-popular matching and compute one, if so. We consider the problem of deciding if $G$ admits a matching that is both popular and $A$-popular and finding one, if so. We call such matchings fully popular. A fully popular matching is useful when $A$ is the more important side -- so along with overall popularity, we would like to maintain ``popularity within the set $A$''. A fully popular matching is not necessarily a min-size/max-siz
Popularity is an approach in mechanism design to find fair structures in a graph, based on the votes of the nodes. Popular matchings are the relaxation of stable matchings: given a graph G=(V,E) with strict preferences on the neighbors of the nodes, a matching M is popular if there is no other matching M' such that the number of nodes preferring M' is more than those preferring M. This paper considers the popularity testing problem, when the task is to decide whether a given matching is popular or not. Previous algorithms applied reductions to maximum weight matchings. We give a new algorithm for testing popularity by reducing the problem to maximum matching testing, thus attaining a linear running time O(|E|). Linear programming-based characterization of popularity is often applied for proving the popularity of a certain matching. As a consequence of our algorithm we derive a more structured dual witness than previous ones. Based on this result we give a combinatorial characterization of fractional popular matchings, which are a special class of popular matchings.
Global popularity (GP) bias is the phenomenon that popular items are recommended much more frequently than they should be, which goes against the goal of providing personalized recommendations and harms user experience and recommendation accuracy. Many methods have been proposed to reduce GP bias but they fail to notice the fundamental problem of GP, i.e., it considers popularity from a \textit{global} perspective of \textit{all users} and uses a single set of popular items, and thus cannot capture the interests of individual users. As such, we propose a user-aware version of item popularity named \textit{personal popularity} (PP), which identifies different popular items for each user by considering the users that share similar interests. As PP models the preferences of individual users, it naturally helps to produce personalized recommendations and mitigate GP bias. To integrate PP into recommendation, we design a general \textit{personal popularity aware counterfactual} (PPAC) framework, which adapts easily to existing recommendation models. In particular, PPAC recognizes that PP and GP have both direct and indirect effects on recommendations and controls direct effects with cou
In news recommendation systems, reducing popularity bias is essential for delivering accurate and diverse recommendations. This paper presents POPK, a new method that uses temporal-counterfactual analysis to mitigate the influence of popular news articles. By asking, "What if, at a given time $t$, a set of popular news articles were competing for the user's attention to be clicked?", POPK aims to improve recommendation accuracy and diversity. We tested POPK on three different language datasets (Japanese, English, and Norwegian) and found that it successfully enhances traditional methods. POPK offers flexibility for customization to enhance either accuracy or diversity, alongside providing distinct ways of measuring popularity. We argue that popular news articles always compete for attention, even if they are not explicitly present in the user's impression list. POPK systematically eliminates the implicit influence of popular news articles during each training step. We combine counterfactual reasoning with a temporal approach to adjust the negative sample space, refining understanding of user interests. Our findings underscore how POPK effectively enhances the accuracy and diversity
We study popularity for matchings under preferences. This solution concept captures matchings that do not lose against any other matching in a majority vote by the agents. A popular matching is said to be robust if it is popular among multiple instances. We present a polynomial-time algorithm for deciding whether there exists a robust popular matching if instances only differ with respect to the preferences of a single agent. The same method applies also to dominant matchings, a subclass of maximum-size popular matchings. By contrast, we obtain NP-completeness if two instances differ only by two agents of the same side or by a swap of two adjacent alternatives by two agents. The first hardness result applies to dominant matchings as well. Moreover, we find another complexity dichotomy based on preference completeness for the case where instances differ by making some options unavailable. We conclude by discussing related models, such as strong and mixed popularity.
The efficient computation of large matchings with desirable guarantees is a crucial objective in market design. However, even in simple two-sided matching markets with weak ordinal preferences, finding a maximum-size stable matching is NP-hard. Alternatively, popular matchings can be of larger size, but their existence is not guaranteed. In this paper, we study a new definition of popularity with two-sided weak preferences, where agents are only indifferent between two matchings if they receive the same partner. We show that this alternative definition of popularity, which we call weak popularity, guarantees the existence of such matchings. Unfortunately, finding a maximum-size weakly popular matching turns out to be NP-hard even with one-sided ties. However, we provide a polynomial-time algorithm to find a weakly popular matching that has at least $\frac{3}{4}$ times the size of a maximum-size weakly popular matching. We complement our approximation results with an Integer Linear Programming formulation that solves the maximum-size weakly popular matching problem exactly. We evaluate our algorithms on both randomly generated and real-world instances. Our experiments demonstrate th
Our input is a directed, rooted graph $G = (V \cup \{r\},E)$ where each vertex in $V$ has a partial order preference over its incoming edges. The preferences of a vertex extend naturally to preferences over arborescences rooted at $r$. We seek a popular arborescence in $G$, i.e., one for which there is no "more popular" arborescence. Popular arborescences have applications in liquid democracy or collective decision making; however, they need not exist in every input instance. The popular arborescence problem is to decide if a given input instance admits a popular arborescence or not. We show a polynomial-time algorithm for this problem, whose computational complexity was not known previously. Our algorithm is combinatorial, and can be regarded as a primal-dual algorithm. It searches for an arborescence along with its dual certificate, a chain of subsets of $E$, witnessing its popularity. In fact, our algorithm solves the more general popular common base problem in the intersection of two matroids, where one matroid is the partition matroid defined by any partition $E = \bigcup_{v\in V} δ(v)$ and the other is an arbitrary matroid on $E$ of rank $|V|$, with each $v \in V$ having a pa
Let G = ((A,B),E) be an instance of the stable marriage problem where every vertex ranks its neighbors in a strict order of preference. A matching M in G is popular if M does not lose a head-to-head election against any matching. Popular matchings are a well-studied generalization of stable matchings, introduced with the goal of enlarging the set of admissible solutions, while maintaining a certain level of fairness. Every stable matching is a min-size popular matching. Unfortunately, when there are edge costs, it is NP-hard to find a popular matching of minimum cost -- even worse, the min-cost popular matching problem is hard to approximate up to any factor. Let opt be the cost of a min-cost popular matching. Our goal is to efficiently compute a matching of cost at most opt by paying the price of mildly relaxing popularity. Our main positive results are two bi-criteria algorithms that find in polynomial time a near-popular or quasi-popular matching of cost at most opt. Moreover, one of the algorithms finds a quasi-popular matching of cost at most that of a min-cost popular fractional matching, which could be much smaller than opt. Key to the other algorithm is a polynomial-size ex
Social scientists have long sought to understand why certain people, items, or options become more popular than others. One seemingly intuitive theory is that inherent value drives popularity. An alternative theory claims that popularity is driven by the rich-get-richer effect of cumulative advantage---certain options become more popular, not because they are higher quality, but because they are already relatively popular. Realistically, it seems likely that popularity is driven by neither one of these forces alone but rather both together. Recently, researchers have begun using large-scale online experiments to study the effect of cumulative advantage in realistic scenarios, but there have been no large-scale studies of the combination of these two effects. We are interested in studying a case where decision-makers observe explicit signals of both the popularity and the quality of various options. We derive a model for change in popularity as a function of past popularity and past perceived quality. Our model implies that we should expect an interaction between these two forces---popularity should amplify the effect of quality, so that the more popular an option is, the faster we
Recent studies have shown that recommendation systems commonly suffer from popularity bias. Popularity bias refers to the problem that popular items (i.e., frequently rated items) are recommended frequently while less popular items are recommended rarely or not at all. Researchers adopted two approaches to examining popularity bias: (i) from the users' perspective, by analyzing how far a recommendation system deviates from user's expectations in receiving popular items, and (ii) by analyzing the amount of exposure that long-tail items receive, measured by overall catalog coverage and novelty. In this paper, we examine the first point of view in the book domain, although the findings may be applied to other domains as well. To this end, we analyze the well-known Book-Crossing dataset and define three user groups based on their tendency towards popular items (i.e., Niche, Diverse, Bestseller-focused). Further, we evaluate the performance of nine state-of-the-art recommendation algorithms and two baselines (i.e., Random, MostPop) from both the accuracy (e.g., NDCG, Precision, Recall) and popularity bias perspectives. Our results indicate that most state-of-the-art recommendation algor
Popular matchings have been intensively studied recently as a relaxed concept of stable matchings. By applying the concept of popular matchings to branchings in directed graphs, Kavitha et al.\ (2020) introduced popular branchings. In a directed graph $G=(V_G,E_G)$, each vertex has preferences over its incoming edges. For branchings $B_1$ and $B_2$ in $G$, a vertex $v\in V_G$ prefers $B_1$ to $B_2$ if $v$ prefers its incoming edge of $B_1$ to that of $B_2$, where having an arbitrary incoming edge is preferred to having none, and $B_1$ is more popular than $B_2$ if the number of vertices that prefer $B_1$ is greater than the number of vertices that prefer $B_2$. A branching $B$ is called a popular branching if there is no branching more popular than $B$. Kavitha et al. (2020) proposed an algorithm for finding a popular branching when the preferences of each vertex are given by a strict partial order. The validity of this algorithm is proved by utilizing classical theorems on the duality of weighted arborescences. In this paper, we generalize popular branchings to weighted popular branchings in vertex-weighted directed graphs in the same manner as weighted popular matchings by Mestre
In this paper, we study the effect of popularity degradation bias in the context of local music recommendations. Specifically, we examine how accurate two top-performing recommendation algorithms, Weight Relevance Matrix Factorization (WRMF) and Multinomial Variational Autoencoder (Mult-VAE), are at recommending artists as a function of artist popularity. We find that both algorithms improve recommendation performance for more popular artists and, as such, exhibit popularity degradation bias. While both algorithms produce a similar level of performance for more popular artists, Mult-VAE shows better relative performance for less popular artists. This suggests that this algorithm should be preferred for local (long-tail) music artist recommendation.
Databases are considered to be integral part of modern information systems. Almost every web or mobile application uses some kind of database. Database management systems are considered to be a crucial element from both business and technological standpoint. This paper divides different types of database management systems into two main categories (relational and non-relational) and several sub categories. Ranking of various sub categories for the month of July, 2021 are presented in the form of popularity score calculated and managed by DB-Engines. Popularity trend for each category is also presented to look at the change in popularity since 2013. Complete ranking and trend of top 20 systems has shown that relational models are still most popular systems with Oracle and MySQL being two most popular systems. However, recent trends have shown DBMSs like Time Series and Document Store getting more and more popular with their wide use in IOT technology and BigData, respectively.
We consider the max-size popular matching problem in a roommates instance G = (V,E) with strict preference lists. A matching M is popular if there is no matching M' in G such that the vertices that prefer M' to M outnumber those that prefer M to M'. We show it is NP-hard to compute a max-size popular matching in G. This is in contrast to the tractability of this problem in bipartite graphs where a max-size popular matching can be computed in linear time. We define a subclass of max-size popular matchings called strongly dominant matchings and show a linear time algorithm to solve the strongly dominant matching problem in a roommates instance. We consider a generalization of the max-size popular matching problem in bipartite graphs: this is the max-weight popular matching problem where there is also an edge weight function w and we seek a popular matching of largest weight. We show this is an NP-hard problem and this is so even when w(e) is either 1 or 2 for every edge e. We also show an algorithm with running time O*(2^{n/4}) to find a max-weight popular matching matching in G = (A U B,E)$ on n vertices.
Let $G = (A \cup B, E)$ be an instance of the stable marriage problem with strict preference lists. A matching $M$ is popular in $G$ if $M$ does not lose a head-to-head election against any matching where vertices are voters. Every stable matching is a min-size popular matching; another subclass of popular matchings that always exist and can be easily computed is the set of dominant matchings. A popular matching $M$ is dominant if $M$ wins the head-to-head election against any larger matching. Thus every dominant matching is a max-size popular matching and it is known that the set of dominant matchings is the linear image of the set of stable matchings in an auxiliary graph. Results from the literature seem to suggest that stable and dominant matchings behave, from a complexity theory point of view, in a very similar manner within the class of popular matchings. The goal of this paper is to show that indeed there are differences in the tractability of stable and dominant matchings, and to investigate further their importance for popular matchings. First, we show that it is easy to check if all popular matchings are also stable, however it is co-NP hard to check if all popular match
Let $G$ be a digraph where every node has preferences over its incoming edges. The preferences of a node extend naturally to preferences over branchings, i.e., directed forests; a branching $B$ is popular if $B$ does not lose a head-to-head election (where nodes cast votes) against any branching. Such popular branchings have a natural application in liquid democracy. The popular branching problem is to decide if $G$ admits a popular branching or not. We give a characterization of popular branchings in terms of dual certificates and use this characterization to design an efficient combinatorial algorithm for the popular branching problem. When preferences are weak rankings, we use our characterization to formulate the popular branching polytope in the original space and also show that our algorithm can be modified to compute a branching with least unpopularity margin. When preferences are strict rankings, we show that "approximately popular" branchings always exist.