Related papers: Pilot evaluation of Collection API with PID Kernel…

Effective item identifiers (IDs) are an important component for recommender systems (RecSys) in practice, and are commonly adopted in many use cases such as retrieval and ranking. IDs can encode collaborative filtering signals within…

Generative recommendation (GR) has gained increasing attention for its promising performance compared to traditional models. A key factor contributing to the success of GR is the semantic ID (SID), which converts continuous semantic…

Online clustering methods that adaptively create and update nodes as data arrive often make node learning explicit, whereas the mapping from the learned node state to output clusters often remains implicit or simplified. Implicit mappings…

Is it possible to design an universal API for federated learning using which an ad-hoc group of data-holders (agents) collaborate with each other and perform federated learning? Such an API would necessarily need to be model-agnostic i.e.…

Domain adaptation aims to assist the modeling tasks of the target domain with knowledge of the source domain. The two domains often lie in different feature spaces due to diverse data collection methods, which leads to the more challenging…

Motion prediction is highly relevant to the perception of dynamic objects and static map elements in the scenarios of autonomous driving. In this work, we propose PIP, the first end-to-end Transformer-based framework which jointly and…

The partial information decomposition (PID) is perhaps the leading proposal for resolving information shared between a set of sources and a target into redundant, synergistic, and unique constituents. Unfortunately, the PID framework has…

Generative retrieval with Semantic IDs (SIDs) assigns each item a discrete identifier and treats retrieval as a sequence generation problem rather than a nearest-neighbor search. While content-only SIDs are stable, they do not take into…

Bivariate Partial Information Decomposition (PID) describes how the mutual information between a random variable M and two random variables Y and Z is decomposed into unique, redundant, and synergistic terms. Recently, PID has shown promise…

Generative Recommendation has revolutionized recommender systems by reformulating retrieval as a sequence generation task over discrete item identifiers. Despite the progress, existing approaches typically rely on static, decoupled…

While mutual information effectively quantifies dependence between two variables, it does not by itself reveal the complex, fine-grained interactions among variables, i.e., how multiple sources contribute redundantly, uniquely, or…

Unsupervised domain adaptive person re-identification (ReID) has been extensively investigated to mitigate the adverse effects of domain gaps. Those works assume the target domain data can be accessible all at once. However, for the…

Partial information decompositions (PIDs), which quantify information interactions between three or more variables in terms of uniqueness, redundancy and synergy, are gaining traction in many application domains. However, our understanding…

Semantic IDs (SIDs) define the generation space of generative recommendation and directly determine its personalization ceiling. However, existing tokenizers are trained independently with retrieval objectives, leaving personalization…

Person re-identification (ReID) is now an active research topic for AI-based video surveillance applications such as specific person search, but the practical issue that the target person(s) may change clothes (clothes inconsistency…

Persistent Homology (PH) is a fundamental tool in computational topology, designed to uncover the intrinsic geometric and topological features of data across multiple scales. Originating within the broader framework of Topological Data…

Training recommender systems for next-item recommendation often requires unique embeddings to be learned for each item, which may take up most of the trainable parameters for a model. Shared embeddings, such as using content information,…

The conservation of cultural heritage increasingly relies on integrating technological innovation with domain expertise to ensure effective monitoring and predictive maintenance. This paper presents a novel framework to support the…

Real-world processes often involve interdependent objects that also carry data values, such as integers, reals, or strings. However, existing process formalisms fall short to combine key modeling features, such as tracking object…

All Control Systems that grow to any size have a variety of data that are stored in different formats on different nodes in the network. Examples include sensor value and status, archived sensor data, device oriented support data and…