Related papers: Learning Behaviorally Grounded Item Embeddings via…
Kernel classifiers and regressors designed for structured data, such as sequences, trees and graphs, have significantly advanced a number of interdisciplinary areas such as computational biology and drug design. Typically, kernels are…
Spatial convolutions are widely used in numerous deep video models. It fundamentally assumes spatio-temporal invariance, i.e., using shared weights for every location in different frames. This work presents Temporally-Adaptive Convolutions…
We introduce a method to provide vectorial representations of visual classification tasks which can be used to reason about the nature of those tasks and their relations. Given a dataset with ground-truth labels and a loss function defined…
In this paper, we propose a novel deep neural network architecture, Sequence-to-Sequence Audio2Vec, for unsupervised learning of fixed-length vector representations of audio segments excised from a speech corpus, where the vectors contain…
Representation learning methods that transform encoded data (e.g., diagnosis and drug codes) into continuous vector spaces (i.e., vector embeddings) are critical for the application of deep learning in healthcare. Initial work in this area…
Process Mining offers a powerful framework for uncovering, analyzing, and optimizing real-world business processes. Petri nets provide a versatile means of modeling process behavior. However, traditional methods often struggle to…
Fine-tuning LLM-based text embedders via contrastive learning maps inputs and outputs into a new representational space, discarding the LLM's output semantics. We propose LLM2Vec-Gen, a self-supervised alternative that instead produces…
Modern AI is opening the door to collective decision-making in which participants express their views as free-form text rather than voting on a fixed set of candidates. A natural idea is to embed these opinions in a vector space so that the…
Recently, self-attention based models have achieved state-of-the-art performance in sequential recommendation task. Following the custom from language processing, most of these models rely on a simple positional embedding to exploit the…
Inspired by diachronic word analysis from the field of natural language processing, we propose an approach for uncovering temporal insights regarding user roles from social networks using graph embedding methods. Specifically, we apply the…
Temporal knowledge graphs represent temporal facts $(s,p,o,\tau)$ relating a subject $s$ and an object $o$ via a relation label $p$ at time $\tau$, where $\tau$ could be a time point or time interval. Temporal knowledge graphs may exhibit…
The egocentric and exocentric viewpoints of a human activity look dramatically different, yet invariant representations to link them are essential for many potential applications in robotics and augmented reality. Prior work is limited to…
Session-based recommendations which predict the next action by understanding a user's interaction behavior with items within a relatively short ongoing session have recently gained increasing popularity. Previous research has focused on…
Incorporating item content information into click-through rate (CTR) prediction models remains a challenge, especially with the time and space constraints of industrial scenarios. The content-encoding paradigm, which integrates user and…
Embedding is a useful technique to project a high-dimensional feature into a low-dimensional space, and it has many successful applications including link prediction, node classification and natural language processing. Current approaches…
Generative AI models, particularly Text-to-Video (T2V) systems, offer a promising avenue for transforming science education by automating the creation of engaging and intuitive visual explanations. In this work, we take a first step toward…
Users consume their favorite content in temporal proximity of consumption bundles according to their preferences and tastes. Thus, the underlying attributes of items implicitly match user preferences, however, current recommender systems…
Although a variety of methods have been proposed for sequential recommendation, it is still far from being well solved partly due to two challenges. First, the existing methods often lack the simultaneous consideration of the global…
There exists a correlation between geospatial activity temporal patterns and type of land use. A novel self-supervised approach is proposed to stratify landscape based on mobility activity time series. First, the time series signal is…
Individual user profiles and interaction histories play a significant role in providing customized experiences in real-world applications such as chatbots, social media, retail, and education. Adaptive user representation learning by…