ETC improves Transformer models for long and structured inputs.
problem Scaling input length and encoding structured inputs in Transformers.
method Introduces global-local attention, relative position encodings, and CPC pre-training.
result Achieves state-of-the-art results on four natural language datasets.
Framework for handling long-tailed multi-modal data.
problem Class imbalance and long-tailed distributions in multi-modal data.
method Multi-expert architecture with modality-specific networks and dynamic fusion weights.
result Framework outperforms existing methods in long-tailed, class-imbalanced scenarios.
HGNet improves GNNs' ability to handle long-range interactions in graphs.
problem Insufficiency of GNNs in capturing long-range interactions.
method Introduces hierarchical message passing models with multi-resolution graph representations.
result HGNet outperforms conventional GNNs in molecular property prediction.
New RNN model handles long-term dependencies in irregularly-sampled time series.
problem Handling long-term dependencies in irregularly-sampled time series data.
method Designing ODE-LSTMs that separate memory from continuous-time state.
result ODE-LSTMs outperform other RNN-based models on non-uniformly sampled data with long-term dependencies.
Rough Transformers improve efficiency for medical time-series data.
problem Efficiently modeling irregularly sampled, long-range time-series data.
method Introducing Rough Transformers, a Transformer variant with continuous-time representations and multi-view signature attention.
result Rough Transformers outperform vanilla Transformers while using less computational resources.
SGM combines deep learning and planning for robust long-horizon tasks.
problem Combining deep learning and planning for robust long-horizon tasks.
method Sparse Graphical Memory (SGM) that stores states and feasible transitions in a sparse memory, aggregating states according to a two-way consistency objective.
result SGM significantly outperforms current state of the art methods on long horizon, sparse-reward visual navigation tasks.
Self-attention prefers sparse functions of input sequences, reducing sample complexity.
problem Understanding the inductive biases of self-attention in modeling long-range dependencies.
method Theoretical analysis and synthetic experiments to probe sample complexity of learning sparse functions with Transformers.
result Bounded-norm Transformer networks can represent sparse functions of the input sequence with logarithmic sample complexity.
Recurrent Neural Networks (RNNs), which are a powerful scheme for modeling temporal and sequential data need to capture long-term dependencies on datasets and represent them in hidden layers with a powerful model to capture more information from inputs. For modeling long-term dependencies in a dataset, the gating mecha…
Model combines long-term and short-term memory using conceptors.
problem Transfer between long-term and short-term memory.
method Recurrent neural network with gated reservoir for short-term memory and conceptors for long-term memory.
result Standard operations on conceptors allow combining long-term memories and describing their effect on short-term memory.
MD-GAN learns long-time molecular behavior from short-time data with multi-particle input.
problem Accurately predicting long-time molecular dynamics from short-time data.
method Machine learning method (MD-GAN) that incorporates dynamics of multiple particles of molecules.
result Predicting diffusion with one-third of the training data length using multi-particle input.
SCROLLS benchmarks long text NLP tasks, improving existing models.
problem Short NLP benchmarks ignore long texts; SCROLLS addresses this.
method Handpicked long-text datasets for summarization, QA, and inference tasks.
result Improvement potential on SCROLLS tasks, as indicated by initial baselines.
New framework calibrates computer models using deep learning and quantile regression.
problem Uncertainty in computer model input parameters due to high-dimensional time series data.
method Deep neural network with long-short term memory layers for inverse modeling, quantile regression for interval predictions.
result Accurate point and interval estimates for input parameters in WRF-hydro model.
Existing methods for arterial blood pressure (BP) estimation directly map the input physiological signals to output BP values without explicitly modeling the underlying temporal dependencies in BP dynamics. As a result, these models suffer from accuracy decay over a long time and thus require frequent calibration. In t…
New interpretation of RNN forget gate improves learnability for long-term sequential data.
problem Improving learnability of recurrent neural networks for long-term temporal dependencies.
method Generalized theory of gated RNNs, focusing on gradient behavior over time.
result Existing RNNs satisfy the gradient condition for initial training, suggesting validity of forget gate interpretation.
We consider reinforcement learning in input-driven environments, where an exogenous, stochastic input process affects the dynamics of the system. Input processes arise in many applications, including queuing systems, robotics control with disturbances, and object tracking. Since the state dynamics and rewards depend on…
LEM efficiently models long-term sequences with gradients.
problem Learning long-term sequential dependencies in data.
method Gradient-based multiscale ordinary differential equations system.
result LEM outperforms state-of-the-art models in various tasks.
Meta-learning improves event prediction from short sequences.
problem Predicting events from short sequences is challenging.
method Meta-learning approach using recurrent neural networks and monotonic neural networks.
result Meta-learning enhances long-term prediction performance.
This paper explores four different visualization techniques for long short-term memory (LSTM) networks applied to continuous-valued time series. On the datasets analysed, we find that the best visualization technique is to learn an input deletion mask that optimally reduces the true class score. With a specific focus o…
Reservoir computing predicts chaotic systems for long horizons with sparse updates.
problem Predicting chaotic systems with long horizons using limited data.
method Sparse, time-dependent data inputs into reservoir computing.
result Achieves arbitrarily long prediction horizons for chaotic systems.
A new RNN model tackles long-time dependencies with fast, invertible, and memory-efficient hidden states.
problem Challenges in processing sequential inputs with long-time dependencies in RNNs.
method A novel RNN architecture based on a Hamiltonian system of oscillators.
result The proposed RNN mitigates exploding and vanishing gradient problems, providing state-of-the-art performance.
Successful recurrent models such as long short-term memories (LSTMs) and gated recurrent units (GRUs) use ad hoc gating mechanisms. Empirically these models have been found to improve the learning of medium to long term temporal dependencies and to help with vanishing gradient issues. We prove that learnable gates in a…
We propose non-stationary spectral kernels for Gaussian process regression. We propose to model the spectral density of a non-stationary kernel function as a mixture of input-dependent Gaussian process frequency density surfaces. We solve the generalised Fourier transform with such a model, and present a family of non-…
TimeBridge addresses non-stationarity in long-term time series forecasting.
problem Non-stationarity in multivariate time series leads to spurious regressions and obscures long-term relationships.
method TimeBridge segments series into patches, applying Integrated Attention for short-term non-stationarity and Cointegrated Attention for long-term cointegration.
result TimeBridge achieves state-of-the-art performance in both short-term and long-term forecasting.
This paper examines biases in foundation models under long-tailed data and proposes a method to mitigate parameter imbalance.
problem The bias introduced by imbalanced training data in foundation models affects long-tailed downstream tasks.
method The paper examines parameter imbalance and data imbalance, proposing a backdoor adjustment method to mitigate parameter imbalance.
result An average performance increase of about 1.67% on each dataset.
Generalizes memory and forecasting capacities for nonlinear recurrent networks with dependent inputs.
problem Understanding memory and forecasting capabilities in networks with dependent inputs.
method Formulated bounds for memory and forecasting capacities in terms of network size and input properties.
result Proved that memory capacity for linear recurrent networks with independent inputs is given by the rank of the controllability matrix.
Introduces Spectral Attention for better long-range time series forecasting.
problem Challenges in capturing long-range dependencies in time series forecasting.
method Spectral Attention mechanism that preserves temporal correlations and long-range dependencies.
result Achieves state-of-the-art results on 11 real-world time series datasets.
Recurrent Neural Networks (RNN), Long Short-Term Memory Networks (LSTM), and Memory Networks which contain memory are popularly used to learn patterns in sequential data. Sequential data has long sequences that hold relationships. RNN can handle long sequences but suffers from the vanishing and exploding gradient probl…
We utilize long-term memory, fractal dimension and approximate entropy as input variables for the Efficiency Index [Kristoufek & Vosvrda (2013), Physica A 392]. This way, we are able to comment on stock market efficiency after controlling for different types of inefficiencies. Applying the methodology on 38 stock marke…
Proposes LSR-IGRU for improved stock trend prediction.
problem Challenges in stock price prediction due to complex relationships and nonlinear dynamics.
method Long short-term relationships matrix and improved GRU input for better temporal and relationship integration.
result Significantly improved accuracy in predicting stock trend changes.
Multivariate techniques based on engineered features have found wide adoption in the identification of jets resulting from hadronic top decays at the Large Hadron Collider (LHC). Recent Deep Learning developments in this area include the treatment of the calorimeter activation as an image or supplying a list of jet con…
Summarization of long sequences into a concise statement is a core problem in natural language processing, requiring non-trivial understanding of the input. Based on the promising results of graph neural networks on highly structured data, we develop a framework to extend existing sequence encoders with a graph compone…
There has been a recent shift in sequence-to-sequence modeling from recurrent network architectures to convolutional network architectures due to computational advantages in training and operation while still achieving competitive performance. For systems having limited long-term temporal dependencies, the approximatio…
Unitary recurrent neural networks (URNNs) have been proposed as a method to overcome the vanishing and exploding gradient problem in modeling data with long-term dependencies. A basic question is how restrictive is the unitary constraint on the possible input-output mappings of such a network? This work shows that for …
Paper proposes a dual-level approach for multi-step forecasting of dynamical systems.
problem Accurate multi-step forecasting of time series systems for automatic control and optimization.
method Hybrid input forecasting using LSTM-STMs and physics-informed neural networks (PINNs).
result Hybrid models achieve higher log-likelihood and lower MSE compared to conventional methods.
Hydra boosts efficiency for long-context reasoning in resource-constrained settings.
problem Quadratic complexity of transformers limits long-context reasoning in resource-constrained systems.
method Hydra uses a modular architecture with adaptive routing between sparse global attention, mixture-of-experts, and dual memories.
result Hydra achieves significant throughput and accuracy improvements for long-context reasoning.
Paper addresses LSTM stability for thermal systems using infinity-norm.
problem Stability of LSTM networks in thermal systems.
method Derived ISS∞ condition for LSTM, developed training strategy. result ISS∞-promoted LSTM outperforms other models in thermal system case study. Global Memory Augmentation (GMAT) improves Transformer performance on long documents.
problem Large memory requirements of Transformer pairwise dot-product attention for long sequences.
method Integrates a dense global memory of length M into sparse Transformer blocks.
result Significant improvement on various tasks, including synthetic tasks, masked language modeling, and reading comprehension.
A novel approach predicts long-term stock price trends using 2D-convolutional encoders and semantic segmentation.
problem Predicting long-term daily stock price changes with deep learning models.
method Proposes a hierarchical CNN structure with Atrous Spatial Pyramid Pooling blocks to capture both long and short-term temporal relationships.
result Achieved overall accuracy and AUC of 78.18% and 0.88 for predicting trends over the next 20 days.
Improved Mamba model for long-range sequence tasks.
problem Mamba's poor performance on long-range sequential tasks.
method Proposed B2S6, combining block-wise selective dynamics and channel-specific bias.
result Empirically, B2S6 outperforms S4 and S4D on LRA tasks.
The standard LSTM recurrent neural networks while very powerful in long-range dependency sequence applications have highly complex structure and relatively large (adaptive) parameters. In this work, we present empirical comparison between the standard LSTM recurrent neural network architecture and three new parameter-r…
The variational autoencoder is a well defined deep generative model that utilizes an encoder-decoder framework where an encoding neural network outputs a non-deterministic code for reconstructing an input. The encoder achieves this by sampling from a distribution for every input, instead of outputting a deterministic c…
We introduce a general method to extract knowledge from a recurrent neural network (Long Short Term Memory) that has learnt to detect if a given input sequence is valid or not, according to an unknown generative automaton. Based on the clustering of the hidden states, we explain how to build and validate an automaton t…
Recurrent sequence generators conditioned on input data through an attention mechanism have recently shown very good performance on a range of tasks in- cluding machine translation, handwriting synthesis and image caption gen- eration. We extend the attention-mechanism with features needed for speech recognition. We sh…
New framework removes harmful momentum effect for long-tailed classification.
problem Challenges in maintaining balanced datasets with long-tailed data.
method Causal inference framework to disentangle and remove harmful effects of momentum.
result Achieves state-of-the-art performance on long-tailed visual recognition benchmarks.
The authors of (Cho et al., 2014a) have shown that the recently introduced neural network translation systems suffer from a significant drop in translation quality when translating long sentences, unlike existing phrase-based translation systems. In this paper, we propose a way to address this issue by automatically se…
Rough Transformers improve time series modeling with lower costs and better performance.
problem Inefficient modeling of irregularly sampled time series data.
method Signature patching for continuous-time representations, reducing computational costs.
result Rough Transformers outperform vanilla Transformers and Neural ODE models.
A novel online GP model captures long-term memory in sequential data.
problem Capturing long-term memory in sequential data online.
method Integrates HiPPO framework into interdomain GP, leveraging time-varying orthogonal projections as inducing variables.
result OHSVGP outperforms existing online GP methods in predictive performance, long-term memory preservation, and computational efficiency.
Study optimizes growth rate for investors with long-only constraints.
problem Maximizing growth rate under drift uncertainty and long-only constraints.
method Developed a finite dimensional approximation for concave functionally generated portfolios.
result Proved uniqueness and existence for optimal portfolios under long-only constraints.