Markus Schedl
YOU?
Author Swipe
View article: Single-Branch Network Architectures to Close the Modality Gap in Multimodal Recommendation
Single-Branch Network Architectures to Close the Modality Gap in Multimodal Recommendation Open
Traditional recommender systems rely on collaborative filtering (CF), using past user–item interactions to help users discover new items in a vast collection. In cold start , i. e., when interaction histories of users or items are not avai…
View article: Music4All A+A
Music4All A+A Open
Music4All A+A: Artist and Album Dataset Music4All A+A (Artist and Album) is a large-scale multimodal dataset for Music Information Retrieval (MIR) tasks, providing comprehensive metadata, genre labels, image representations, and textual de…
View article: Just Ask for Music (JAM): Multimodal and Personalized Natural Language Music Recommendation
Just Ask for Music (JAM): Multimodal and Personalized Natural Language Music Recommendation Open
Natural language interfaces offer a compelling approach for music recommendation, enabling users to express complex preferences conversationally. While Large Language Models (LLMs) show promise in this direction, their scalability in recom…
View article: Parameter-Efficient Single Collaborative Branch for Recommendation
Parameter-Efficient Single Collaborative Branch for Recommendation Open
Recommender Systems (RS) often rely on representations of users and items in a joint embedding space and on a similarity metric to compute relevance scores. In modern RS, the modules to obtain user and item representations consist of two d…
View article: Hybrid Personalization Using Declarative and Procedural Memory Modules of the Cognitive Architecture ACT-R
Hybrid Personalization Using Declarative and Procedural Memory Modules of the Cognitive Architecture ACT-R Open
Recommender systems often rely on sub-symbolic machine learning approaches that operate as opaque black boxes. These approaches typically fail to account for the cognitive processes that shape user preferences and decision-making. In this …
View article: Chameleon: A Multimodal Learning Framework Robust to Missing Modalities
Chameleon: A Multimodal Learning Framework Robust to Missing Modalities Open
Multimodal learning has demonstrated remarkable performance improvements over unimodal architectures. However, multimodal learning methods often exhibit deteriorated performances if one or more modalities are missing. This may be attribute…
View article: PAEFF: Precise Alignment and Enhanced Gated Feature Fusion for Face-Voice Association
PAEFF: Precise Alignment and Enhanced Gated Feature Fusion for Face-Voice Association Open
We study the task of learning association between faces and voices, which is gaining interest in the multimodal community lately. These methods suffer from the deliberate crafting of negative mining procedures as well as the reliance on th…
View article: Music4All-Onion
Music4All-Onion Open
Music4All-Onion is a large-scale, multi-modal music dataset that expands the Music4All dataset by including 26 additional audio, video, and metadata features for 109,269 music pieces and provides a set of 252,984,396 listening records of 1…
View article: Familiarizing with Music: Discovery Patterns for Different Music Discovery Needs
Familiarizing with Music: Discovery Patterns for Different Music Discovery Needs Open
Humans have the tendency to discover and explore. This natural tendency is reflected in data from streaming platforms as the amount of previously unknown content accessed by users. Additionally, in domains such as that of music streaming t…
View article: Unsupervised Graph Embeddings for Session-based Recommendation with Item Features
Unsupervised Graph Embeddings for Session-based Recommendation with Item Features Open
In session-based recommender systems, predictions are based on the user's preceding behavior in the session. State-of-the-art sequential recommendation algorithms either use graph neural networks to model sessions in a graph or leverage th…
View article: Nuanced Music Emotion Recognition via a Semi-Supervised Multi-Relational Graph Neural Network
Nuanced Music Emotion Recognition via a Semi-Supervised Multi-Relational Graph Neural Network Open
Music emotion recognition (MER) seeks to understand the complex emotional landscapes elicited by music, acknowledging music’s profound social and psychological roles beyond traditional tasks such as genre classification or content similari…
View article: Introduction to the Special Issue on Trustworthy Recommender Systems
Introduction to the Special Issue on Trustworthy Recommender Systems Open
This editorial introduces the Special Issue on Trustworthy Recommender Systems , hosted by the ACM Transactions on Recommender Systems in 2024. We provide an overview on the multifaceted aspects of trustworthiness and point to recent regul…
View article: Simultaneous Unlearning of Multiple Protected User Attributes From Variational Autoencoder Recommenders Using Adversarial Training
Simultaneous Unlearning of Multiple Protected User Attributes From Variational Autoencoder Recommenders Using Adversarial Training Open
In widely used neural network-based collaborative filtering models, users' history logs are encoded into latent embeddings that represent the users' preferences. In this setting, the models are capable of mapping users' protected attribute…
View article: Oh, Behave! Country Representation Dynamics Created by Feedback Loops in Music Recommender Systems
Oh, Behave! Country Representation Dynamics Created by Feedback Loops in Music Recommender Systems Open
Recent work suggests that music recommender systems are prone to\ndisproportionally frequent recommendations of music from countries more\nprominently represented in the training data, notably the US. However, it\nremains unclear to what e…
View article: Unlabeled Debiasing in Downstream Tasks via Class-wise Low Variance Regularization
Unlabeled Debiasing in Downstream Tasks via Class-wise Low Variance Regularization Open
Language models frequently inherit societal biases from their training data. Numerous techniques have been proposed to mitigate these biases during both the pre-training and fine-tuning stages. However, fine-tuning a pre-trained debiased l…
View article: The Importance of Cognitive Biases in the Recommendation Ecosystem
The Importance of Cognitive Biases in the Recommendation Ecosystem Open
Cognitive biases have been studied in psychology, sociology, and behavioral economics for decades. Traditionally, they have been considered a negative human trait that leads to inferior decision-making, reinforcement of stereotypes, or can…
View article: Modality Invariant Multimodal Learning to Handle Missing Modalities: A Single-Branch Approach
Modality Invariant Multimodal Learning to Handle Missing Modalities: A Single-Branch Approach Open
Multimodal networks have demonstrated remarkable performance improvements over their unimodal counterparts. Existing multimodal networks are designed in a multi-branch fashion that, due to the reliance on fusion strategies, exhibit deterio…