Search Results for author:
Found 27 papers, 12 papers with code
Att-Adapter: A Robust and Precise Domain-Specific Multi-Attributes T2I Diffusion Adapter via Conditional Variational Autoencoder
To address this, we introduce the Attribute (Att) Adapter, a novel plug-and-play module designed to enable fine-grained, multi-attributes control in pretrained diffusion models.
Vertical Validation: Evaluating Implicit Generative Models for Graphs on Thin Support Regions
There has been a growing excitement that implicit graph generative models could be used to design or discover new molecules for medicine or material design.
Counterfactual Fairness by Combining Factual and Counterfactual Predictions
To fill in this gap, we provide a theoretical study on the inherent trade-off between CF and predictive performance in a model-agnostic manner.
Decoupled Vertical Federated Learning for Practical Training on Vertically Partitioned Data
Vertical Federated Learning (VFL) is an emergent distributed machine learning paradigm for collaborative learning between clients who have disjoint features of common entities.
StarCraftImage: A Dataset For Prototyping Spatial Reasoning Methods For Multi-Agent Environments
Spatial reasoning tasks in multi-agent environments such as event prediction, agent type identification, or missing data imputation are important for multiple applications (e. g., autonomous surveillance over sensor networks and subtasks for reinforcement learning (RL)).
Fault Tolerant Serverless VFL Over Dynamic Device Environment
Vertical Federated learning (VFL) is a class of FL where each client shares the same set of samples but only owns a subset of the features.
Towards Practical Non-Adversarial Distribution Matching
Distribution matching can be used to learn invariant representations with applications in fairness and robustness.
Benchmarking Algorithms for Federated Domain Generalization
We then apply our methodology to evaluate 14 Federated DG methods, which include centralized DG methods adapted to the FL context, FL methods that handle client heterogeneity, and methods designed specifically for Federated DG.
Towards Characterizing Domain Counterfactuals For Invertible Latent Causal Models
Answering counterfactual queries has important applications such as explainability, robustness, and fairness but is challenging when the causal variables are unobserved and the observations are non-linear mixtures of these latent variables, such as pixels in images.
Enhanced Controllability of Diffusion Models via Feature Disentanglement and Realism-Enhanced Sampling Methods
Second, we propose timestep-dependent weight scheduling for content and style features to further improve the performance.
Towards Explaining Distribution Shifts
We derive our interpretable mappings from a relaxation of optimal transport, where the candidate mappings are restricted to a set of interpretable mappings.
Cooperative Distribution Alignment via JSD Upper Bound
Unsupervised distribution alignment estimates a transformation that maps two or more source distributions to a shared aligned distribution given only samples from each distribution.
Discrete Tree Flows via Tree-Structured Permutations
While normalizing flows for continuous data have been extensively researched, flows for discrete data have only recently been explored.
Resilience to Multiple Attacks via Adversarially Trained MIMO Ensembles
We show that ensemble methods can improve adversarial robustness to multiple attacks if the ensemble is \emph{adversarially diverse}, which is defined by two properties: 1) the sub-models are adversarially robust themselves and yet 2) adversarial attacks do not transfer easily between sub-models.
Feature Shift Detection: Localizing Which Features Have Shifted via Conditional Distribution Tests
While previous distribution shift detection approaches can identify if a shift has occurred, these approaches cannot localize which specific features have caused a distribution shift -- a critical step in diagnosing or fixing any underlying issue.
Why be adversarial? Let's cooperate!: Cooperative Dataset Alignment via JSD Upper Bound
Unsupervised dataset alignment estimates a transformation that maps two or more source domains to a shared aligned domain given only the domain datasets.
Iterative Alignment Flows
Existing flow-based approaches estimate multiple flows independently, which is equivalent to learning multiple full generative models.
Shapley Explanation Networks
This intrinsic explanation approach enables layer-wise explanations, explanation regularization of the model during training, and fast explanation computation at test time.
Exploring Adversarial Examples via Invertible Neural Networks
We propose a new way of achieving such understanding through a recent development, namely, invertible neural models with Lipschitz continuous mapping functions from the input to the output.
Automated Dependence Plots
To address these drawbacks, we formalize a method for automating the selection of interesting PDPs and extend PDPs beyond showing single features to show the model response along arbitrary directions, for example in raw feature space or a latent space arising from some generative model.
On the (In)fidelity and Sensitivity of Explanations
We analyze optimal explanations with respect to both these measures, and while the optimal explanation for sensitivity is a vacuous constant explanation, the optimal explanation for infidelity is a novel combination of two popular explanation methods.
On the (In)fidelity and Sensitivity for Explanations
We analyze optimal explanations with respect to both these measures, and while the optimal explanation for sensitivity is a vacuous constant explanation, the optimal explanation for infidelity is a novel combination of two popular explanation methods.
A Review of Multivariate Distributions for Count Data Derived from the Poisson Distribution
The Poisson distribution has been widely studied and used for modeling univariate count-valued data.
Generalized Root Models: Beyond Pairwise Graphical Models for Univariate Exponential Families
As in the recent work with square root graphical (SQR) models [Inouye et al. 2016]---which was restricted to pairwise dependencies---we give the conditions of the parameters that are needed for normalization using the radial conditionals similar to the pairwise case [Inouye et al. 2016].
Square Root Graphical Models: Multivariate Generalizations of Univariate Exponential Families that Permit Positive Dependencies
With this motivation, we give an example of our model class derived from the univariate exponential distribution that allows for almost arbitrary positive and negative dependencies with only a mild condition on the parameter matrix---a condition akin to the positive definiteness of the Gaussian covariance matrix.
Fixed-Length Poisson MRF: Adding Dependencies to the Multinomial
We show the effectiveness of our LPMRF distribution over Multinomial models by evaluating the test set perplexity on a dataset of abstracts and Wikipedia.
Capturing Semantically Meaningful Word Dependencies with an Admixture of Poisson MRFs
We develop a fast algorithm for the Admixture of Poisson MRFs (APM) topic model and propose a novel metric to directly evaluate this model.
