Search Results for author:
Found 41 papers, 20 papers with code
Multi Task Inverse Reinforcement Learning for Common Sense Reward
One of the challenges in applying reinforcement learning in a complex real-world environment lies in providing the agent with a sufficiently detailed reward function.
Improved Generalization of Weight Space Networks via Augmentations
Learning in deep weight spaces (DWS), where neural networks process the weights of other neural networks, is an emerging research direction, with applications to 2D and 3D neural fields (INRs, NeRFs), as well as making inferences about other types of neural networks.
Bayesian Uncertainty for Gradient Aggregation in Multi-Task Learning
Running a dedicated model for each task is computationally expensive and therefore there is a great interest in multi-task learning (MTL).
Data Augmentations in Deep Weight Spaces
Learning in weight spaces, where neural networks process the weights of other deep neural networks, has emerged as a promising research direction with applications in various fields, from analyzing and editing neural fields and implicit neural representations, to network pruning and quantization.
Equivariant Deep Weight Space Alignment
To accelerate the alignment process and improve its quality, we propose a novel framework aimed at learning to solve the weight alignment problem, which we name Deep-Align.
Object-Centric Open-Vocabulary Image-Retrieval with Aggregated Features
Our approach aggregates dense embeddings extracted from CLIP into a compact representation, essentially combining the scalability of image retrieval pipelines with the object identification capabilities of dense detection methods.
Learning Discrete Weights and Activations Using the Local Reparameterization Trick
In computer vision and machine learning, a crucial challenge is to lower the computation and memory demands for neural network inference.
GD-VDM: Generated Depth for better Diffusion-based Video Generation
GD-VDM is based on a two-phase generation process involving generating depth videos followed by a novel diffusion Vid2Vid model that generates a coherent real-world video.
LipVoicer: Generating Speech from Silent Videos Guided by Lip Reading
We then condition a diffusion model on the video and use the extracted text through a classifier-guidance mechanism where a pre-trained ASR serves as the classifier.
DisCLIP: Open-Vocabulary Referring Expression Generation
Our results highlight the potential of using pre-trained visual-semantic models for generating high-quality contextual descriptions.
Guided Deep Kernel Learning
Combining Gaussian processes with the expressive power of deep neural networks is commonly done nowadays through deep kernel learning (DKL).
Auxiliary Learning as an Asymmetric Bargaining Game
Auxiliary learning is an effective method for enhancing the generalization capabilities of trained models, particularly when dealing with small datasets.
Equivariant Architectures for Learning in Deep Weight Spaces
Designing machine learning architectures for processing neural networks in their raw weight matrix form is a newly introduced research direction.
Communication Efficient Distributed Learning over Wireless Channels
Vertical distributed learning exploits the local features collected by multiple learning workers to form a better global model.
A Study on the Evaluation of Generative Models
In this work, we study the evaluation metrics of generative models by generating a high-quality synthetic dataset on which we can estimate classical metrics for comparison.
Functional Ensemble Distillation
Bayesian models have many desirable properties, most notable is their ability to generalize from limited data and to properly estimate the uncertainty in their predictions.
Multi-Task Learning as a Bargaining Game
In this paper, we propose viewing the gradients combination step as a bargaining game, where tasks negotiate to reach an agreement on a joint direction of parameter update.
Ranked #1 on
Multi-Task Learning
on Cityscapes test
Can Stochastic Gradient Langevin Dynamics Provide Differential Privacy for Deep Learning?
Bayesian learning via Stochastic Gradient Langevin Dynamics (SGLD) has been suggested for differentially private learning.
Personalized Federated Learning with Gaussian Processes
A key challenge in this setting is to learn effectively across clients even though each client has unique data that is often limited in size.
Ranked #1 on
Personalized Federated Learning
on CIFAR-100
Personalized Federated Learning using Hypernetworks
In this approach, a central hypernetwork model is trained to generate a set of models, one model for each client.
Ranked #1 on
Personalized Federated Learning
on CIFAR-10
GP-Tree: A Gaussian Process Classifier for Few-Shot Incremental Learning
As a result, our method scales well with both the number of classes and data size.
Scene-Agnostic Multi-Microphone Speech Dereverberation
We use noisy and noiseless versions of a simulated reverberant dataset to test the proposed architecture.
From Local Structures to Size Generalization in Graph Neural Networks
In this paper, we identify an important type of data where generalization from small to large graphs is challenging: graph distributions for which the local structure depends on the graph size.
Learning the Pareto Front with Hypernetworks
Here, we tackle the problem of learning the entire Pareto front, with the capability of selecting a desired operating point on the front after training.
On Size Generalization in Graph Neural Networks
We further demonstrate on several tasks, that training GNNs on small graphs results in solutions which do not generalize to larger graphs.
Auxiliary Learning by Implicit Differentiation
Two main challenges arise in this multi-task learning setting: (i) designing useful auxiliary tasks; and (ii) combining auxiliary tasks into a single coherent loss.
Restoration of Fragmentary Babylonian Texts Using Recurrent Neural Networks
The main source of information regarding ancient Mesopotamian history and culture are clay cuneiform tablets.
On Learning Sets of Symmetric Elements
We first characterize the space of linear layers that are equivariant both to element reordering and to the inherent symmetries of elements, like translation in the case of images.
Understanding the Limitations of Conditional Generative Models
Class-conditional generative models hold promise to overcome the shortcomings of their discriminative counterparts.
Evaluating and Calibrating Uncertainty Prediction in Regression Tasks
Predicting not only the target but also an accurate measure of uncertainty is important for many machine learning applications and in particular safety-critical ones.
On the Universality of Invariant Networks
We conclude the paper by proving a necessary condition for the universality of $G$-invariant networks that incorporate only first-order tensors.
Incremental Few-Shot Learning with Attention Attractor Networks
This paper addresses this problem, incremental few-shot learning, where a regular classification network has already been trained to recognize a set of base classes, and several extra novel classes are being considered, each with only a few labeled examples.
Neural Guided Constraint Logic Programming for Program Synthesis
Synthesizing programs using example input/outputs is a classic problem in artificial intelligence.
Inference in Probabilistic Graphical Models by Graph Neural Networks
Message-passing algorithms, such as belief propagation, are a natural way to disseminate evidence amongst correlated variables while exploiting the graph structure, but these algorithms can struggle when the conditional dependency graphs contain loops.
Reviving and Improving Recurrent Back-Propagation
We examine all RBP variants along with BPTT and TBPTT in three different application domains: associative memory with continuous Hopfield networks, document classification in citation networks using graph neural networks and hyperparameter optimization for fully connected networks.
Neural Relational Inference for Interacting Systems
Interacting systems are prevalent in nature, from dynamical systems in physics to complex societal dynamics.
Learning Discrete Weights Using the Local Reparameterization Trick
We show how a simple modification to the local reparameterization trick, previously used to train Gaussian distributed weights, enables the training of discrete weights.
Human Pose Estimation using Deep Consensus Voting
In this paper we consider the problem of human pose estimation from a single still image.
Ranked #37 on
Pose Estimation
on MPII Human Pose
Unsupervised Ensemble Learning with Dependent Classifiers
In unsupervised ensemble learning, one obtains predictions from multiple sources or classifiers, yet without knowing the reliability and expertise of each source, and with no labeled data to assess it.
Learning Local Invariant Mahalanobis Distances
For many tasks and data types, there are natural transformations to which the data should be invariant or insensitive.
Graph Approximation and Clustering on a Budget
We consider the problem of learning from a similarity matrix (such as spectral clustering and lowd imensional embedding), when computing pairwise similarities are costly, and only a limited number of entries can be observed.
