Artificial neural networks suffer from catastrophic forgetting when they are sequentially trained on multiple tasks. To overcome this problem, we present a novel approach based on task-conditioned hypernetworks, i.e., networks that generate the weights of a target model based on task identity. Continual learning (CL) i…
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,657 papers · 148 categories
Trend · papers per month
17 results for “task-conditional”
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.
We study how to leverage off-the-shelf visual and linguistic data to cope with out-of-vocabulary answers in visual question answering task. Existing large-scale visual datasets with annotations such as image class labels, bounding boxes and region descriptions are good sources for learning rich and diverse visual conce…
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.
The goal of optimization-based meta-learning is to find a single initialization shared across a distribution of tasks to speed up the process of learning new tasks. Conditional meta-learning seeks task-specific initialization to better capture complex task distributions and improve performance. However, many existing c…
Neural architecture search has recently attracted lots of research efforts as it promises to automate the manual design of neural networks. However, it requires a large amount of computing resources and in order to alleviate this, a performance prediction network has been recently proposed that enables efficient archit…
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.
We show how the problem of estimating conditional Kendall's tau can be rewritten as a classification task. Conditional Kendall's tau is a conditional dependence parameter that is a characteristic of a given pair of random variables. The goal is to predict whether the pair is concordant (value of ) or discordant (val…
Despite recent success of deep network-based Reinforcement Learning (RL), it remains elusive to achieve human-level efficiency in learning novel tasks. While previous efforts attempt to address this challenge using meta-learning strategies, they typically suffer from sampling inefficiency with on-policy RL algorithms o…
Few-shot learning has become essential for producing models that generalize from few examples. In this work, we identify that metric scaling and metric task conditioning are important to improve the performance of few-shot algorithms. Our analysis reveals that simple metric scaling completely changes the nature of few-…
The paper characterizes brain states and transitions using functional MRI data.
problem Characterizing the dynamic reconfiguration of neural systems in brain states.
method Bayesian model-based characterization of latent brain states and posterior predictive discrepancy using the latent block model.
result The model detects transitions between latent brain states and identifies distinctive community patterns in task-fMRI data.
Self-supervised learning improves by predicting known information, reducing labeled data needs.
problem Efficiently learn useful semantic representations without labeled data.
method Develops a mechanism exploiting statistical connections between pretext tasks to learn representations that solve downstream tasks.
result Proves linear layer yields small approximation error and drastically reduces labeled sample complexity.
Kernel density matrices simplify probabilistic deep learning.
problem Representing joint probability distributions of continuous and discrete variables.
method Extending density matrices to a reproducing kernel Hilbert space.
result Versatile representation for marginal and joint probability distributions.
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.
AI benchmarks evaluate football team performance using generative models.
problem Evaluating human performance in complex interactive tasks is error-prone and unreliable.
method Trained Conditional VRNN Model on player and ball tracking data to imitate and predict team interactions.
result Trained model as a useful benchmark for evaluating team performance in football.
Unified framework detects dynamic community structure in brain networks across individuals.
problem Detecting community structure in functional brain networks across multiple subjects and over time.
method Markov-switching stochastic block model (MSS-SBM) for multilayer brain networks.
result Captures dynamic reconfiguration of modular connectivity in brain networks across different task conditions.
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.