Related papers: Deep Models of Interactions Across Sets
Molecule representation learning is crucial for understanding and predicting molecular properties. However, conventional atom-centric models, which treat chemical bonds merely as pairwise interactions, often overlook complex bond-level…
What does it mean for a machine to recognize beauty? While beauty remains a culturally and experientially compelling but philosophically elusive concept, deep learning systems increasingly appear capable of modeling aesthetic judgment. In…
We study the problem of learning permutation invariant representations that can capture "flexible" notions of containment. We formalize this problem via a measure theoretic definition of multisets, and obtain a theoretically-motivated…
Over the past decade, deep learning has proven to be a highly effective tool for learning meaningful features from raw data. However, it remains an open question how deep networks perform hierarchical feature learning across layers. In this…
Recent deep-learning models have achieved impressive predictive performance by learning complex functions of many variables, often at the cost of interpretability. This chapter covers recent work aiming to interpret models by attributing…
This paper investigates the idea of encoding object-centered representations in the design of the reward function and policy architectures of a language-guided reinforcement learning agent. This is done using a combination of object-wise…
Cross-domain recommendation has long been one of the major topics in recommender systems. Recently, various deep models have been proposed to transfer the learned knowledge across domains, but most of them focus on extracting abstract…
Transformers are deep neural network architectures that underpin the recent successes of large language models. Unlike more classical architectures that can be viewed as point-to-point maps, a Transformer acts as a measure-to-measure map…
In this paper, we propose to provide a general ensemble learning framework based on deep learning models. Given a group of unit models, the proposed deep ensemble learning framework will effectively combine their learning results via a…
In this paper we present a unified framework for modeling multi-relational representations, scoring, and learning, and conduct an empirical study of several recent multi-relational embedding models under the framework. We investigate the…
This paper presents the design of deep learning architectures which allow to classify the social relationship existing between two people who are walking in a side-by-side formation into four possible categories --colleagues, couple, family…
To plan safe maneuvers and act with foresight, autonomous vehicles must be capable of accurately predicting the uncertain future. In the context of autonomous driving, deep neural networks have been successfully applied to learning…
Human vision models are at the core of image processing. For instance, classical approaches to the problem of image quality are based on models that include knowledge about human vision. However, nowadays, deep learning approaches have…
Recognizing spatial relations and reasoning about them is essential in multiple applications including navigation, direction giving and human-computer interaction in general. Spatial relations between objects can either be explicit --…
Identifying common patterns among events is a key ability in human and machine perception, as it underlies intelligent decision making. We propose an approach for learning semantic relational set abstractions on videos, inspired by human…
Deep metric learning maps visually similar images onto nearby locations and visually dissimilar images apart from each other in an embedding manifold. The learning process is mainly based on the supplied image negative and positive training…
Speech encodes a wealth of information related to human behavior and has been used in a variety of automated behavior recognition tasks. However, extracting behavioral information from speech remains challenging including due to inadequate…
Humans learn about objects via interaction and using multiple perceptions, such as vision, sound, and touch. While vision can provide information about an object's appearance, non-visual sensors, such as audio and haptics, can provide…
Machine learning models have become firmly established across all scientific fields. Extracting features from data and making inferences based on them with neural network models often yields high accuracy; however, this approach has several…
The functions of proteins and RNAs are determined by a myriad of interactions between their constituent residues, but most quantitative models of how molecular phenotype depends on genotype must approximate this by simple additive effects.…