Search Results for author:
Found 66 papers, 18 papers with code
Spatio-Temporal Forecasting of PM2.5 via Spatial-Diffusion guided Encoder-Decoder Architecture
One such example is forecasting the concentration of fine particulate matter (PM2. 5) in the atmosphere which is influenced by many complex factors, the most important ones being diffusion due to meteorological factors as well as transport across vast distances over a period of time.
Federated Learning with Uncertainty and Personalization via Efficient Second-order Optimization
Moreover, Bayesian FL also naturally enables personalization in FL to handle data heterogeneity across the different clients by having each client learn its own distinct personalized model.
RISSOLE: Parameter-efficient Diffusion Models via Block-wise Generation and Retrieval-Guidance
To this end, we design a retrieval-augmented generation (RAG) approach and leverage the corresponding blocks of the images retrieved by the RAG module to condition the training and generation stages of a block-wise denoising diffusion model.
Robust Black-box Testing of Deep Neural Networks using Co-Domain Coverage
We present a novel black-box coverage criterion called Co-Domain Coverage (CDC), which is defined as a function of the model's output and thus takes into account its end-to-end behavior.
VERSE: Virtual-Gradient Aware Streaming Lifelong Learning with Anytime Inference
Streaming lifelong learning is a challenging setting of lifelong learning with the goal of continuous learning in a dynamic non-stationary environment without forgetting.
A Probabilistic Framework for Lifelong Test-Time Adaptation
Test-time adaptation (TTA) is the problem of updating a pre-trained source model at inference time given test input(s) from a different target domain.
Novel Class Discovery without Forgetting
Inspired by this, we identify and formulate a new, pragmatic problem setting of NCDwF: Novel Class Discovery without Forgetting, which tasks a machine learning model to incrementally discover novel categories of instances from unlabeled data, while maintaining its performance on the previously seen categories.
Federated Learning with Uncertainty via Distilled Predictive Distributions
In many situations, however, especially in limited data settings, it is beneficial to take into account the uncertainty in the model parameters at each client as it leads to more accurate predictions and also because reliable estimates of uncertainty can be used for tasks, such as out-of-distribution (OOD) detection, and sequential decision-making tasks, such as active learning.
Spacing Loss for Discovering Novel Categories
Novel Class Discovery (NCD) is a learning paradigm, where a machine learning model is tasked to semantically group instances from unlabeled data, by utilizing labeled instances from a disjoint set of classes.
Semi-Supervised Super-Resolution
The proposed semi-supervised technique can be used as a plug-and-play module with any supervised GAN-based Super-Resolution method to enhance its performance.
DiffuseVAE: Efficient, Controllable and High-Fidelity Generation from Low-Dimensional Latents
Diffusion probabilistic models have been shown to generate state-of-the-art results on several competitive image synthesis benchmarks but lack a low-dimensional, interpretable latent space, and are slow at generation.
Ranked #20 on
Image Generation
on CelebA 64x64
SITA: Single Image Test-time Adaptation
In Test-time Adaptation (TTA), given a source model, the goal is to adapt it to make better predictions for test instances from a different distribution than the source.
NeurInt : Learning to Interpolate through Neural ODEs
In this work, we propose a novel generative model that learns a flexible non-parametric prior over interpolation trajectories, conditioned on a pair of source and target images.
Hypernetworks for Continual Semi-Supervised Learning
Further, we present $\textit{Semi-Split CIFAR-10}$, a new benchmark for continual semi-supervised learning, obtained by modifying the $\textit{Split CIFAR-10}$ dataset, in which the tasks with labelled and unlabelled data arrive sequentially.
NeurInt-Learning Interpolation by Neural ODEs
A range of applications require learning image generation models whose latent space effectively captures the high-level factors of variation in the data distribution, which can be judged by its ability to interpolate between images smoothly.
Fine-Grained Emotion Prediction by Modeling Emotion Definitions
In this paper, we propose a new framework for fine-grained emotion prediction in the text through emotion definition modeling.
Knowledge Consolidation based Class Incremental Online Learning with Limited Data
In our approach, we learn robust representations that are generalizable across tasks without suffering from the problems of catastrophic forgetting and overfitting to accommodate future classes with limited samples.
Rectification-based Knowledge Retention for Continual Learning
Our proposed method uses weight rectifications and affine transformations in order to adapt the model to different tasks that arrive sequentially.
Variational Rejection Particle Filtering
We present a variational inference (VI) framework that unifies and leverages sequential Monte-Carlo (particle filtering) with \emph{approximate} rejection sampling to construct a flexible family of variational distributions.
Efficient Feature Transformations for Discriminative and Generative Continual Learning
However, the growth in the number of additional parameters of many of these types of methods can be computationally expensive at larger scales, at times prohibitively so.
CAM-GAN: Continual Adaptation Modules for Generative Adversarial Networks
Our approach is based on learning a set of global and task-specific parameters.
Few-Shot Lifelong Learning
Our method selects very few parameters from the model for training every new set of classes instead of training the full model.
Quantile Regularization : Towards Implicit Calibration of Regression Models
We provide a detailed formal analysis of the \emph{side-effects} of Isotonic Regression when used for regression calibration.
Partial Rejection Control for Robust Variational Inference in Sequential Latent Variable Models
Effective variational inference crucially depends on a flexible variational family of distributions.
A Unified Bayesian Framework for Discriminative and Generative Continual Learning
Two notable directions among the recent advances in continual learning with neural networks are (1) variational Bayes based regularization by learning priors from previous tasks, and, (2) learning the structure of deep networks to adapt to new tasks.
Calibrating CNNs for Lifelong Learning
Further, our approach does not require storing data samples from the old tasks, which is done by many replay based methods.
Towards Zero-Shot Learning with Fewer Seen Class Examples
We present a meta-learning based generative model for zero-shot learning (ZSL) towards a challenging setting when the number of training examples from each \emph{seen} class is very few.
Temperature Scaling for Quantile Calibration
Deep learning models are often poorly calibrated, i. e., they may produce overconfident predictions that are wrong, implying that their uncertainty estimates are unreliable.
Generalized Adversarially Learned Inference
Recent approaches, such as ALI and BiGAN frameworks, develop methods of inference of latent variables in GANs by adversarially training an image generator along with an encoder to match two joint distributions of image and latent vector pairs.
P-SIF: Document Embeddings Using Partition Averaging
One of the key reasons is that a longer document is likely to contain words from many different topics; hence, creating a single vector while ignoring all the topical structure is unlikely to yield an effective document representation.
Graph Representation Learning via Ladder Gamma Variational Autoencoders
In addition to leveraging the representational power of multiple layers of stochastic variables via the ladder VAE architecture, our framework offers the following benefits: (1) Unlike existing ladder VAE architectures based on real-valued latent variables, the gamma-distributed latent variables naturally result in non-negativity and sparsity of the learned embeddings, and facilitate their direct interpretation as membership of nodes into (possibly multiple) communities/topics; (2) A novel recognition model for our gamma ladder VAE architecture allows fast inference of node embeddings; and (3) The framework also extends naturally to incorporate node side information (features and/or labels).
Quantile Regularization: Towards Implicit Calibration of Regression Models
It is therefore desirable to have models that produce predictive uncertainty estimates that are reliable.
A "Network Pruning Network" Approach to Deep Model Compression
The pruner is essentially a multitask deep neural network with binary outputs that help identify the filters from each layer of the original network that do not have any significant contribution to the model and can therefore be pruned.
Deep Attentive Ranking Networks for Learning to Order Sentences
We apply our framework on two tasks: Sentence Ordering and Order Discrimination.
Jointly Trained Image and Video Generation using Residual Vectors
The proposed model allows minor variations in content across frames while maintaining the temporal dependence through latent vectors encoding the pose or motion features.
On the relationship between multitask neural networks and multitask Gaussian Processes
Despite the effectiveness of multitask deep neural network (MTDNN), there is a limited theoretical understanding on how the information is shared across different tasks in MTDNN.
Bayesian Structure Adaptation for Continual Learning
Two notable directions among the recent advances in continual learning with neural networks are ($i$) variational Bayes based regularization by learning priors from previous tasks, and, ($ii$) learning the structure of deep networks to adapt to new tasks.
Learning to Recommend from Sparse Data via Generative User Feedback
To address this, we propose a learning framework that improves collaborative filtering with a synthetic feedback loop (CF-SFL) to simulate the user feedback.
Refined $α$-Divergence Variational Inference via Rejection Sampling
Our inference method is based on a crucial observation that $D_\infty(p||q)$ equals $\log M(\theta)$ where $M(\theta)$ is the optimal value of the RS constant for a given proposal $q_\theta(x)$.
A Meta-Learning Framework for Generalized Zero-Shot Learning
Our proposed model yields significant improvements on standard ZSL as well as more challenging GZSL setting.
A Generative Framework for Zero-Shot Learning with Adversarial Domain Adaptation
Our approach is based on end-to-end learning of the class distributions of seen classes and unseen classes.
Ranked #1 on
Zero-Shot Learning
on CUB-200 - 0-Shot Learning
(using extra training data)
Stochastic Blockmodels meet Graph Neural Networks
Although we develop this framework for a particular type of SBM, namely the \emph{overlapping} stochastic blockmodel, the proposed framework can be adapted readily for other types of SBMs.
Play and Prune: Adaptive Filter Pruning for Deep Model Compression
Our framework, called Play and Prune (PP), jointly prunes and fine-tunes CNN model parameters, with an adaptive pruning rate, while maintaining the model's predictive performance.
Variational Autoencoders for Sparse and Overdispersed Discrete Data
Many applications, such as text modelling, high-throughput sequencing, and recommender systems, require analysing sparse, high-dimensional, and overdispersed discrete (count-valued or binary) data.
Generative Model for Zero-Shot Sketch-Based Image Retrieval
We present a probabilistic model for Sketch-Based Image Retrieval (SBIR) where, at retrieval time, we are given sketches from novel classes, that were not present at training time.
Deep Topic Models for Multi-label Learning
We present a probabilistic framework for multi-label learning based on a deep generative model for the binary label vector associated with each observation.
HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs
We present a novel deep learning architecture in which the convolution operation leverages heterogeneous kernels.
Leveraging Filter Correlations for Deep Model Compression
We present a filter correlation based model compression approach for deep convolutional neural networks.
Incorporating Syntactic and Semantic Information in Word Embeddings using Graph Convolutional Networks
Word embeddings have been widely adopted across several NLP applications.
Small-Variance Asymptotics for Nonparametric Bayesian Overlapping Stochastic Blockmodels
The latent feature relational model (LFRM) is a generative model for graph-structured data to learn a binary vector representation for each node in the graph.
A Generative Approach to Zero-Shot and Few-Shot Action Recognition
In particular, we assume that the distribution parameters for any action class in the visual space can be expressed as a linear combination of a set of basis vectors where the combination weights are given by the attributes of the action class.
Generalized Zero-Shot Learning via Synthesized Examples
Our model's ability to generate and leverage examples from unseen classes to train the classification model naturally helps to mitigate the bias towards predicting seen classes in generalized zero-shot learning settings.
Zero-Shot Learning via Class-Conditioned Deep Generative Models
We present a deep generative model for learning to predict classes not seen at training time.
Leveraging Distributional Semantics for Multi-Label Learning
Our approach is novel in that it highlights interesting connections between label embedding methods used for multi-label learning and paragraph/document embedding methods commonly used for learning representations of text data.
A Deep Generative Framework for Paraphrase Generation
In this paper, we address the problem of generating paraphrases automatically.
Scalable Generative Models for Multi-label Learning with Missing Labels
We present a scalable, generative framework for multi-label learning with missing labels.
A Simple Exponential Family Framework for Zero-Shot Learning
We model each class-conditional distribution as an exponential family distribution and the parameters of the distribution of each seen/unseen class are defined as functions of the respective observed class attributes.
Deep Generative Models for Relational Data with Side Information
Moreover, inference cost scales in the number of edges which is attractive for massive but sparse networks.
Earliness-Aware Deep Convolutional Networks for Early Time Series Classification
Unlike most existing methods for early classification of time series data, that are designed to solve this problem under the assumption of the availability of a good set of pre-defined (often hand-crafted) features, our framework can jointly perform feature learning (by learning a deep hierarchy of \emph{shapelets} capturing the salient characteristics in each time series), along with a dynamic truncation model to help our deep feature learning architecture focus on the early parts of each time series.
Large-Scale Bayesian Multi-Label Learning via Topic-Based Label Embeddings
We present a scalable Bayesian multi-label learning model based on learning low-dimensional label embeddings.
Scalable Bayesian Non-Negative Tensor Factorization for Massive Count Data
We present a Bayesian non-negative tensor factorization model for count-valued tensor data, and develop scalable inference algorithms (both batch and online) for dealing with massive tensors.
Zero-Truncated Poisson Tensor Factorization for Massive Binary Tensors
We present a scalable Bayesian model for low-rank factorization of massive tensors with binary observations.
Simultaneously Leveraging Output and Task Structures for Multiple-Output Regression
In this paper, we present a multiple-output regression model that leverages the covariance structure of the functions (i. e., how the multiple functions are related with each other) as well as the conditional covariance structure of the outputs.
Co-regularized Multi-view Spectral Clustering
In many clustering problems, we have access to multiple views of the data each of which could be individually used for clustering.
Message-Passing for Approximate MAP Inference with Latent Variables
We consider a general inference setting for discrete probabilistic graphical models where we seek maximum a posteriori (MAP) estimates for a subset of the random variables (max nodes), marginalizing over the rest (sum nodes).
Multi-Label Prediction via Sparse Infinite CCA
Canonical Correlation Analysis (CCA) is a useful technique for modeling dependencies between two (or more) sets of variables.
