New method improves meta-learning performance by task-specific initialization.
problem Difficulties in generalizing and achieving theoretical guarantees in conditional meta-learning.
method Structured prediction approach for task-specific initialization.
result TASML improves performance of existing meta-learning models.
Conditional meta-learning improves meta-learning performance in diverse task environments.
problem Meta-learning struggles with tasks that have heterogeneous complexity.
method Conditional meta-learning infers a task-specific meta-parameter vector.
result Conditional meta-learning outperforms standard meta-learning in diverse task environments.
Task-conditioned hypernetworks help neural networks learn multiple tasks without forgetting.
problem Catastrophic forgetting in neural networks when sequentially trained on multiple tasks.
method Task-conditioned hypernetworks that generate target model weights based on task identity.
result Task-conditioned hypernetworks achieve state-of-the-art performance on CL benchmarks and retain long memories.
Extends neural diffusion processes for multi-task regression.
problem Limited to single-task inference, existing formulations cannot capture dependencies across related tasks.
method Introduces a task encoder to condition diffusion model on low-dimensional representations of context observations.
result Improves predictive performance and uncertainty calibration across related functions.
TDS provides exact samples for conditional distributions in diffusion models.
problem Lack of exact sampling methods for diffusion models.
method Sequential Monte Carlo (SMC) algorithm with twisting technique.
result TDS offers more accurate approximations with fewer particles compared to heuristics.
Task-adaptive clustering improves few-shot learning with unlabeled data.
problem Handling unseen tasks with limited labeled data.
method Task-conditioned clustering in a new projection space.
result State-of-the-art semi-supervised few-shot classification performance.
Auxiliary Tuning adapts pre-trained models for novel tasks efficiently.
problem Adapting pre-trained models for new tasks efficiently.
method Supplementing pre-trained model with an auxiliary model that shifts output distribution.
result Achieved similar results to training from scratch with fewer resources.
Improved NLP performance with fewer parameters and less data using conditional multi-task learning.
problem Challenges in transferring knowledge across different NLP tasks, including overfitting, forgetting, and negative transfer.
method Proposes a novel Transformer architecture with conditional attention and task-conditioned modules for efficient parameter sharing and mitigating forgetting.
result Achieves state-of-the-art performance on 26 NLP tasks with 66% less data and 50% fewer parameters compared to existing methods.
Meta-learning bound uses conditional mutual information.
problem Bounding generalization performance in meta-learning.
method Extends CMI framework to meta-learning with a meta-supersample.
result Explicit bound involving two CMI terms.
Extends neural network approximations to guarantee continuity of real-world learning tasks.
problem Guaranteeing continuity of real-world learning tasks given by conditional expectations.
method Establishing conditions on learning tasks that guarantee their continuity under a factorization of the data-generating process.
result Conditions guaranteeing the continuity of practically any derived learning task.
TADAM improves few-shot learning by task-dependent metric scaling.
problem Improving few-shot learning models with limited data.
method Task-dependent metric scaling and co-training.
result State-of-the-art performance on mini-Imagenet and new CIFAR100 dataset.
New framework estimates demand responses across multiple contexts with limited price variation.
problem Estimating heterogeneous linear price-response functions across multiple contexts with limited price variation and confounding.
method Meta-learning framework that identifies conditional mean of task-specific causal demand parameters given a subset of task-specific observables.
result Improved recovery of demand responses relative to standard transfer-learning baselines.
DCASE 2022 Task 2 tackles domain shifts in ASD for machine condition monitoring.
problem Domain shifts change acoustic characteristics, affecting ASD performance.
method Domain generalization techniques to detect anomalies across unknown domains.
result Two types of domain generalization techniques were identified and analyzed.
Proposes Mv-TCNN for continual learning without known tasks in advance.
problem Catastrophic forgetting in continual learning.
method Multi-view Task Conditional Neural Networks (Mv-TCNN).
result Outperforms state-of-the-art continual learning models.
TOPPO improves PPO for MTRL by balancing critic gradients, outperforming SAC.
problem Critic-side gradient ill-conditioning in PPO for MTRL.
method Critic Balancing modules to improve gradient conditioning and balance task updates.
result TOPPO achieves stronger mean and tail-task performance than SAC-family and ARS-family baselines.
Algorithm transfers visual concepts to answer out-of-vocabulary questions.
problem Leveraging off-the-shelf visual and linguistic data for out-of-vocabulary answers in visual question answering.
method Unsupervised task discovery for learning task conditional visual classifier, then transferring to visual question answering models.
result Algorithm generalizes to out-of-vocabulary answers successfully.
New algorithms find conditions and linear rules with high probability and loss.
problem Finding conditions and rules with high probability and loss in conditional sparse regression.
method Efficient algorithms for identifying conditions and rules with optimal probability and loss.
result Achieved algorithms that nearly match the probability of the ideal condition and improve the approximation to the target loss.
This work improves transferability by considering conditional distributions in feature representations.
problem Improving transferability across multiple domains by considering conditional distributions.
method Introducing von Neumann conditional divergence to quantify the functional dependence between features and desired response.
result Favorable performance in terms of smaller generalization error and less catastrophic forgetting.
New metric predicts neural network reliability under novel conditions.
problem Verifying neural networks' safety in novel scenarios.
method ML Dependability metric, Task Undependability, Harmful Undependability.
result Accurately predicts reliability under novel conditions.
New framework prevents forgetting in sequential learning tasks.
problem Catastrophic forgetting in Convolutional Neural Networks.
method Conditional channel gating modules and task classifier.
result Consistent improvement over existing methods in continual learning.
Self-guiding diffusion models improve time series forecasting, refinement, and generation.
problem Improving time series forecasting, refinement, and generation.
method Unconditionally-trained diffusion model with self-guidance mechanism.
result TSDiff outperforms task-specific conditional forecasting methods and maintains generative performance.
CNAPs adapts image classifiers to new tasks efficiently.
problem Adapting image classifiers to new tasks after initial training.
method Conditional Neural Adaptive Processes (CNAPs) using a modulated classifier and adaptation network.
result CNAPs achieves state-of-the-art results on Meta-Dataset, demonstrating robust transfer-learning.
DDN models flexible free-form conditional distributions.
problem Difficulty in explicitly approximating arbitrary conditional distributions.
method Deconvolutional neural network framework for discretizing continuous domains.
result DDN outperforms other density-estimation methods on various tasks.
Proposes a new model for joint probability distributions in computer vision.
problem Limitation of existing models in meeting diverse downstream tasks.
method Uses parametric conditional probability distributions for each group of variables conditioned on the rest.
result Models can be used for any downstream task without task-specific design.
Paper improves sample efficiency of transfer learning in diffusion models.
problem Diffusion models need too much data to train from scratch.
method Assumes shared low-dimensional representation across tasks for improved sample efficiency.
result Sample complexity of target tasks can be reduced with a well-learned representation.
DCASE 2021 ASD task tackles domain-shifted anomalous sound detection.
problem Detecting unknown anomalous sounds under domain-shifted conditions.
method Ensemble of outlier exposure and inlier modeling detectors, feature learning from machine identification.
result Two types of remarkable approaches were adopted by top teams.
Paper discusses ASD challenge for machine condition monitoring.
problem Detecting unknown anomalous sounds without labeled data.
method Design and evaluation of a large-scale ASD dataset, novel approaches.
result Several novel approaches developed, evaluation results analyzed.
NC learns all conditional distributions of a random vector.
problem Learning all conditional distributions of a random vector.
method Adversarial training to match each conditional distribution.
result NC generalizes to sample from conditional distributions never seen.
DSE learns transferable skills across changing dynamics and goals.
problem Learning transferable skills across different reinforcement learning tasks.
method Variational inference for multi-task reinforcement learning with shared and task-specific latent spaces.
result Policies can generalize to unseen dynamics and goals conditions.
FiLM layers improve visual reasoning tasks by modulating features.
problem Visual reasoning tasks that require multi-step, high-level processes.
method General-purpose FiLM layers that apply feature-wise linear transformations based on conditioning information.
result FiLM layers reduce error by half on the CLEVR benchmark and improve feature coherence.
Estimates task difficulty and transferability without trained models.
problem Estimating the difficulty and transferability of supervised classification tasks.
method Information theoretic approach using conditional entropy between training labels.
result Hardness and transferability estimates correlate with empirical values.
Method solves long-horizon robotic tasks via imitation and reinforcement learning.
problem Long-horizon robotic tasks with complex sequences of actions.
method Two-phase approach: imitation learning followed by reinforcement learning.
result Method can scale to challenging long-horizon tasks.
RCNPs extend equivariant neural processes to higher dimensions, improving performance on tasks with inherent symmetries.
problem Inherently equivariant tasks in spatio-temporal modeling, Bayesian Optimization, and continuous control.
method Relational Conditional Neural Processes (RCNPs) that extend equivariances to higher dimensions.
result Empirically competitive performance on tasks with equivariances.
Paper introduces c-Glow for efficient structured output learning.
problem Intractable computation of conditional likelihood in structured prediction models.
method Conditional Glow (c-Glow) - a conditional generative flow that computes p(y|x) exactly and efficiently.
result c-Glow outperforms state-of-the-art baselines in structured prediction tasks.
Paper tackles robust knowledge transfer in parallel RL tasks.
problem Transfer knowledge from low-tier to high-tier tasks in parallel RL without shared dynamics or reward functions.
method Identifies Optimal Value Dominance condition and proposes online learning algorithms for both tasks.
result Achieves constant regret on partial states and near-optimal regret when tasks are dissimilar.
Agent learns causal relationships from visual data to perform tasks.
problem Performing tasks in novel environments with latent causal structures.
method Learning-based approach to induce causal graphs from visual observations, using attention mechanisms.
result Effective generalization to new tasks with unseen causal structures.
Develops CLDS models to model neural activity with nonlinear dynamics.
problem Complex, nonlinear dynamics in neural population activity.
method Conditionally Linear Dynamical System (CLDS) models using Gaussian Process (GP) priors.
result CLDS models can perform well even in data-limited conditions.
A new framework enables real-time task trade-off control.
problem Conflict between multiple related tasks in a fixed model capacity.
method Formulates MTL as a preference-conditioned multiobjective optimization problem; uses a hypernetwork-based neural network.
result A single model can handle different trade-off preferences among multiple tasks.
CPVs enable efficient learning and generalization of complex tasks.
problem Learning and generalizing complex tasks efficiently.
method Compositional plan vectors (CPVs) for efficient task composition and generalization.
result CPVs enable efficient learning and generalization of complex tasks without additional supervision.
Theoretical analysis shows pretext-based self-supervised learning can be boosted by downstream data under certain conditions.
problem Theoretical analysis of pretext-based self-supervised learning and downstream data refinement.
method Theoretical analysis and experiments on synthetic and real-world datasets.
result Theoretical lower bounds and experiments show that downstream data refinement can boost or hurt performance depending on conditions.
Adversarial ASV improves speaker verification robustness.
problem Mismatches in training, enrollment, and test conditions degrade deep speaker embeddings.
method Adversarial multi-task training to learn condition-invariant embeddings.
result 8.8% and 14.5% relative EER improvements for known and unknown conditions.
Mobile health data predicts chronic conditions better than daily activity.
problem Improving chronic condition prediction accuracy.
method Intra-day step and sleep data from mobile health devices, Convolutional Neural Networks, multi-task learning.
result Intra-day activity data significantly improves chronic condition classification.
CondMTL improves toxicity detection by learning group-specific representations.
problem Algorithmic bias in toxic language detection across demographic groups.
method Conditional Multi-Task Learning (CondMTL) for demographic-specific tasks.
result CondMTL improves predictive recall for minority demographic groups.
Proposes a new Q-learning method to improve sample complexity.
problem Improving sample complexity in Q-learning with limited data.
method Integrates Q-function from a source task into a target task under safe conditions.
result The method converges faster than standard Q-learning under certain conditions.
Meta-learning improves with explicit modeling of task covariate distributions.
problem Ignoring the relationship between task covariates and conditional distributions limits meta-learning performance.
method Introducing a hierarchical Bayesian model that leverages samples from the marginal task covariates to better infer optimal parameters.
result Our method outperforms initialization-based meta-learning on popular classification benchmarks.
We study learning problems in which the conditional distribution of the output given the input varies as a function of additional task variables. In varying-coefficient models with Gaussian process priors, a Gaussian process generates the functional relationship between the task variables and the parameters of this con…
New method learns disentangled representations from ECG data for VT origin classification.
problem Challenges in learning subject-specific models from ECG data due to inter-subject variations.
method Conditional Variational Autoencoder (VAE) with maximum mean discrepancy regularization and contrastive regularization.
result Demonstrated efficacy in classifying VT origin segments compared to standard VAE.
Framework fine-tunes foundation models with semi-supervised learning for downstream tasks and latent spaces.
problem Training foundation models with limited labelled data.
method Mutual information decomposition for downstream and latent spaces, semi-supervised fine-tuning.
result Significant improvements in classification tasks under low-labelled conditions.