Search Results for author:
Found 36 papers, 19 papers with code
Assessing Neural Network Representations During Training Using Noise-Resilient Diffusion Spectral Entropy
Entropy and mutual information in neural networks provide rich information on the learning process, but they have proven difficult to compute reliably in high dimensions.
Generalized Schrödinger Bridge Matching
Modern distribution matching algorithms for training diffusion or flow models directly prescribe the time evolution of the marginal distributions between two boundary distributions.
Graph topological property recovery with heat and wave dynamics-based features on graphs
In this paper, we propose Graph Differential Equation Network (GDeNet), an approach that harnesses the expressive power of solutions to PDEs on a graph to obtain continuous node- and graph-level representations for various downstream tasks.
Weisfeiler and Leman Go Measurement Modeling: Probing the Validity of the WL Test
The expressive power of graph neural networks is usually measured by comparing how many pairs of graphs or nodes an architecture can possibly distinguish as non-isomorphic to those distinguishable by the $k$-dimensional Weisfeiler-Leman ($k$-WL) test.
On Kinetic Optimal Probability Paths for Generative Models
We investigate Kinetic Optimal (KO) Gaussian paths and offer the following observations: (i) We show the KE takes a simplified form on the space of Gaussian paths, where the data is incorporated only through a single, one dimensional scalar function, called the \emph{data separation function}.
Neural FIM for learning Fisher Information Metrics from point cloud data
Although data diffusion embeddings are ubiquitous in unsupervised learning and have proven to be a viable technique for uncovering the underlying intrinsic geometry of data, diffusion embeddings are inherently limited due to their discrete nature.
Assessing Neural Network Representations During Training Using Data Diffusion Spectra
We also see that there is an increase in DSMI with the class label over time.
Hyperbolic Image-Text Representations
Visual and linguistic concepts naturally organize themselves in a hierarchy, where a textual concept "dog" entails all images that contain dogs.
Latent Discretization for Continuous-time Sequence Compression
We empirically verify our approach on multiple domains involving compression of video and motion capture sequences, showing that our approaches can automatically achieve reductions in bit rates by learning how to discretize.
Flow Matching for Generative Modeling
These paths are more efficient than diffusion paths, provide faster training and sampling, and result in better generalization.
Ranked #5 on
Density Estimation
on CIFAR-10
Matching Normalizing Flows and Probability Paths on Manifolds
Continuous Normalizing Flows (CNFs) are a class of generative models that transform a prior distribution to a model distribution by solving an ordinary differential equation (ODE).
Semi-Discrete Normalizing Flows through Differentiable Tessellation
Mapping between discrete and continuous distributions is a difficult task and many have had to resort to heuristical approaches.
Can I see an Example? Active Learning the Long Tail of Attributes and Relations
Using this framing, we introduce an active sampling method that asks for examples from the tail of the data distribution and show that it outperforms classical active learning methods on Visual Genome.
Learning Complex Geometric Structures from Data with Deep Riemannian Manifolds
We present Deep Riemannian Manifolds, a new class of neural network parameterized Riemannian manifolds that can represent and learn complex geometric structures.
Moser Flow: Divergence-based Generative Modeling on Manifolds
MF also produces a CNF via a solution to the change-of-variable formula, however differently from other CNF methods, its model (learned) density is parameterized as the source (prior) density minus the divergence of a neural network (NN).
Neural Spatio-Temporal Point Processes
We propose a new class of parameterizations for spatio-temporal point processes which leverage Neural ODEs as a computational method and enable flexible, high-fidelity models of discrete events that are localized in continuous time and space.
Learning Neural Event Functions for Ordinary Differential Equations
The existing Neural ODE formulation relies on an explicit knowledge of the termination time.
CURI: A Benchmark for Productive Concept Learning Under Uncertainty
Humans can learn and reason under substantial uncertainty in a space of infinitely many concepts, including structured relational concepts ("a scene with objects that have the same color") and ad-hoc categories defined through goals ("objects that could fall on one's head").
Riemannian Continuous Normalizing Flows
Normalizing flows have shown great promise for modelling flexible probability distributions in a computationally tractable way.
Learning Multivariate Hawkes Processes at Scale
Multivariate Hawkes Processes (MHPs) are an important class of temporal point processes that have enabled key advances in understanding and predicting social information systems.
Revisiting the Evaluation of Theory of Mind through Question Answering
Theory of mind, i. e., the ability to reason about intents and beliefs of agents is an important task in artificial intelligence and central to resolving ambiguous references in natural language dialogue.
Hyperbolic Graph Neural Networks
Learning from graph-structured data is an important task in machine learning and artificial intelligence, for which Graph Neural Networks (GNNs) have shown great promise.
Task-Driven Modular Networks for Zero-Shot Compositional Learning
When extending the evaluation to the generalized setting which accounts also for pairs seen during training, we discover that naive baseline methods perform similarly or better than current approaches.
Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings
Moreover -- and in contrast with other methods -- the hierarchical nature of hyperbolic space allows us to learn highly efficient representations and to improve the taxonomic consistency of the inferred hierarchies.
Learning Continuous Hierarchies in the Lorentz Model of Hyperbolic Geometry
We are concerned with the discovery of hierarchical relationships from large-scale unstructured similarity scores.
Hearst Patterns Revisited: Automatic Hypernym Detection from Large Text Corpora
Methods for unsupervised hypernym detection may broadly be categorized according to two paradigms: pattern-based and distributional methods.
Separating Self-Expression and Visual Content in Hashtag Supervision
The variety, abundance, and structured nature of hashtags make them an interesting data source for training vision models.
Fast Linear Model for Knowledge Graph Embeddings
This paper shows that a simple baseline based on a Bag-of-Words (BoW) representation learns surprisingly good knowledge graph embeddings.
Learning Visually Grounded Sentence Representations
We introduce a variety of models, trained on a supervised image captioning corpus to predict the image features for a given caption, to perform sentence representation grounding.
Complex and Holographic Embeddings of Knowledge Graphs: A Comparison
Embeddings of knowledge graphs have received significant attention due to their excellent performance for tasks like link prediction and entity resolution.
Poincaré Embeddings for Learning Hierarchical Representations
Representation learning has become an invaluable approach for learning from symbolic data such as text and graphs.
Ranked #2 on
Link Prediction
on WordNet
Holographic Embeddings of Knowledge Graphs
Learning embeddings of entities and relations is an efficient and versatile method to perform machine learning on relational data such as knowledge graphs.
Ranked #8 on
Link Prediction
on FB15k
A Review of Relational Machine Learning for Knowledge Graphs
In this paper, we provide a review of how such statistical models can be "trained" on large knowledge graphs, and then used to predict new facts about the world (which is equivalent to predicting new edges in the graph).
Reducing the Rank in Relational Factorization Models by Including Observable Patterns
Tensor factorizations have become popular methods for learning from multi-relational data.
Logistic Tensor Factorization for Multi-Relational Data
Tensor factorizations have become increasingly popular approaches for various learning tasks on structured data.
