Proposes GPCA module for channel attention in CNNs using Gaussian processes.
problem Improving performance in visual tasks through effective channel selection.
method Integrates Gaussian processes into channel attention mechanisms for probabilistic modeling of channel correlations.
result Demonstrates improved performance of GPCA module in end-to-end CNN training.
New techniques improve channel prediction in noisy wireless systems.
problem Predicting channels in wireless communication systems from noisy observations.
method Adapted sequence-to-sequence models and transformers with reverse positional encoding and reversed encoder outputs.
result Improved robustness and relationship capture in channel prediction models.
A-MMSE uses attention to learn efficient OFDM channel estimation.
problem Accurate OFDM channel estimation requires second-order statistics, which are hard to obtain in practice.
method A-MMSE is a model-based DNN framework that learns linear MMSE filters via Attention Transformer, reducing inference complexity.
result A-MMSE outperforms other methods in normalized MSE across various SNR conditions.
Paper proposes integrating wavelet transform, channel attention, and LSTM for better stock price prediction.
problem Inherently difficult stock price prediction due to low signal-to-noise ratio.
method Wavelet transform convolution, channel attention, and LSTM integration.
result Robust performance in post-pandemic market conditions.
Tiled Squeeze-and-Excite improves channel attention with local spatial context.
problem Improving channel attention mechanisms in neural networks.
method Proposes tiled squeeze-and-excite (TSE) framework for channel attention.
result Local context of 7 rows or columns is sufficient for matching global context performance.
Attention mechanism is a hot spot in deep learning field. Using channel attention model is an effective method for improving the performance of the convolutional neural network. Squeeze-and-Excitation block takes advantage of the channel dependence, selectively emphasizing the important channels and compressing the rel…
Supervised deep learning has gained significant attention for speech enhancement recently. The state-of-the-art deep learning methods perform the task by learning a ratio/binary mask that is applied to the mixture in the time-frequency domain to produce the clean speech. Despite the great performance in the single-chan…
Two-layer NN with channel attention learns low-degree spherical polynomials efficiently.
problem Learning low-degree spherical polynomials with over-parameterized neural networks.
method Two-layer neural network with channel attention, vanilla gradient descent, learnable channel selection.
result Minimally improved sample complexity of $n \asymp Θ(d^{\ell_0}/\eps)$ for learning low-degree polynomials.
Enhances Transformer models for multivariate time series with dataset-specific channel masks.
problem Capturing channel dependency in multivariate time series models.
method Introduces partial channel dependence and channel masks to refine channel dependency in Transformers.
result Improves model performance across diverse tasks and datasets.
FEM improves attention mechanisms by applying value-driven log-linear tilts.
problem Standard attention mechanisms read via convex average, limiting channel-wise selection.
method Free Energy Mixer (FEM) applies a value-driven, per-channel log-linear tilt to a fast prior over indices.
result FEM outperforms strong baselines on NLP, vision, and time-series tasks.
Sentinel improves time series forecasting by modeling both temporal and channel dependencies.
problem Limited effectiveness of existing transformer-based architectures in multivariate time-series forecasting.
method Proposes Sentinel, a full transformer-based architecture with multi-patch attention mechanism.
result Sentinel achieves better or comparable performance compared to state-of-the-art approaches.
Attention operators have been widely applied in various fields, including computer vision, natural language processing, and network embedding learning. Attention operators on graph data enables learnable weights when aggregating information from neighboring nodes. However, graph attention operators (GAOs) consume exces…
A new distillation method transfers channel information from teacher to student.
problem Transfer knowledge from teacher to student with fewer parameters and calculations.
method Channel Distillation (CD) and Guided Knowledge Distillation (GKD) with loss decay.
result Achieved 27.68% top-1 error on ImageNet with ResNet18, outperforming state-of-the-art methods.
Compression techniques for deep neural networks are important for implementing them on small embedded devices. In particular, channel-pruning is a useful technique for realizing compact networks. However, many conventional methods require manual setting of compression ratios in each layer. It is difficult to analyze th…
IETNet identifies important channels for MVTS classification.
problem Multivariate time series classification with blackbox deep networks.
method End-to-end network combining temporal feature extraction, variable selection, and interaction.
result IETNet improves model accuracy and reduces overfitting by identifying and removing non-predictive variables.
Customers are usually exposed to online digital advertisement channels, such as email marketing, display advertising, paid search engine marketing, along their way to purchase or subscribe products( aka. conversion). The marketers track all the customer journey data and try to measure the effectiveness of each advertis…
In this paper, we propose a model for the Environment Sound Classification Task (ESC) that consists of multiple feature channels given as input to a Deep Convolutional Neural Network (CNN) with Attention mechanism. The novelty of the paper lies in using multiple feature channels consisting of Mel-Frequency Cepstral Coe…
Paper proposes neural network for efficient MIMO channel estimation and pilot reduction.
problem High overhead from pilot transmission in wideband MIMO systems.
method Neural network architecture for frequency-aware pilot design and channel estimation, with pruning technique.
result Neural network outperforms linear minimum mean square error (LMMSE) estimation.
Deep learning model classifies concurrent human interactions from WiFi data with high accuracy.
problem Classifying concurrent human interactions from WiFi data with high accuracy.
method Attention-BiGRU deep learning model using Multiple Input Multiple Output radio link.
result Maximum benchmark accuracy of 94% for a single subject-pair, 88% for ten subject pairs.
A new model classifies multi-lead ECGs better than single-channel models.
problem Classifying multi-lead ECGs for accurate diagnosis.
method Channel-wise attention mechanism in CNNs for multi-lead ECG classification.
result The model achieves better sensitivity and precision than plain ResNet models.
Sound source separation has attracted attention from Music Information Retrieval(MIR) researchers, since it is related to many MIR tasks such as automatic lyric transcription, singer identification, and voice conversion. In this paper, we propose an intuitive spectrogram-based model for source separation by adapting U-…
Machine learning techniques have recently received significant attention as promising approaches to deal with the optical channel impairments, and in particular, the nonlinear effects. In this work, a machine learning-based classification technique, known as the Parzen window (PW) classifier, is applied to mitigate the…
We investigate connections between information-theoretic and estimation-theoretic quantities in vector Poisson channel models. In particular, we generalize the gradient of mutual information with respect to key system parameters from the scalar to the vector Poisson channel model. We also propose, as another contributi…
DSF improves EEG model robustness to missing channels and noise.
problem Robust learning from corrupted EEG data with missing channels.
method Dynamic Spatial Filtering (DSF) as a multi-head attention module.
result DSF achieves up to 29.4% accuracy improvement over baseline models in noisy conditions.
SAMformer improves transformer performance in time series forecasting.
problem Transformers struggle with multivariate long-term forecasting.
method Sharpness-aware minimization and channel-wise attention.
result SAMformer surpasses state-of-the-art methods in multivariate time series forecasting.
Predicts cryptocurrency pump probability using sequence-based neural networks.
problem Detecting pump-and-dump schemes in cryptocurrency markets.
method Developed a sequence-based neural network (SNN) that encodes historical P&D events into sequences for prediction.
result SNN improves prediction accuracy by leveraging positional attention to extract useful information.
Massive multiple-input multiple-output (MIMO) systems require downlink channel state information (CSI) at the base station (BS) to better utilize the available spatial diversity and multiplexing gains. However, in a frequency division duplex (FDD) massive MIMO system, CSI feedback overhead degrades the overall spectral…
Study online learning of quantum processes, showing feasibility for certain types.
problem Learning quantum processes adaptively, especially for bounded gate complexity and Pauli channels.
method Online learning, mistake-bounded model, multiplicative weights update algorithm, Bell sampling.
result Online learning feasible for quantum channels of bounded gate complexity and Pauli channels.
The task of accelerating large neural networks on general purpose hardware has, in recent years, prompted the use of channel pruning to reduce network size. However, the efficacy of pruning based approaches has since been called into question. In this paper, we turn to distillation for model compression---specifically,…
A framework for multi-agent communication over noisy channels in reinforcement learning.
problem Effective communication between multiple agents in a noisy environment.
method A novel multi-agent partially observable Markov decision process (MA-POMDP) framework considering noisy communication channels.
result Jointly learned policies outperform separate learning of communication and decision making.
GSAN learns adaptive node representations using geometric scattering and attention.
problem Oversmoothing in node representation learning.
method Attention-based architecture integrating geometric scattering and GCN channels.
result GSAN outperforms previous networks in semi-supervised node classification.
Transformers without skip connections collapse token representations to a single direction.
problem Rapid convergence of token representations to a single direction in self-attention-only Transformers.
method Analysis of layer normalization, residual connections, and multi-head attention mechanisms.
result Residual connections prevent rank collapse in real Transformers, while MLPs generate new feature directions.
ESE-FN improves elderly activity recognition accuracy.
problem Recognizing individual actions and human-object interactions in elderly activities.
method Exploits multi-modal features from RGB videos and skeleton sequences using ESE attentions and a new Multi-modal Loss.
result ESE-FN achieves best accuracy on ETRI-Activity3D dataset.
Model detects electricity theft with high accuracy.
problem Detecting electricity theft on imbalanced datasets.
method Multi-head self-attention mechanism with dilated convolutions and binary mask.
result Achieved AUC of 0.926, improving previous work by 17%.
Proposes a novel model for healthcare and SME credit risk prediction.
problem Lack of guidance from global view in sequence representation learning for time series modeling.
method Hierarchical Global View-guided (HGV) sequence representation learning framework with GGE and β-Attn modules. result Competitive prediction performance compared with other known baselines.
This work explains the structural origins of attention sinks in LLMs.
problem Initial tokens disproportionately monopolize attention scores in LLMs.
method Traced to self-attention's value aggregation process and FFN layer activations.
result Attention sinks form due to variance discrepancy and dimension disparity.
As a lossy compression framework, compressed sensing has drawn much attention in wireless telemonitoring of biosignals due to its ability to reduce energy consumption and make possible the design of low-power devices. However, the non-sparseness of biosignals presents a major challenge to compressed sensing. This study…
This paper proposes a new approach to Transformers by integrating hierarchical associative memory with MetaFormers.
problem Theoretical framework for Transformers and MLP-Mixers remains underdeveloped.
method Integrating hierarchical associative memory with MetaFormers to create a parallelized MLP-Mixer.
result Symmetry-breaking effects improve the performance of the MLP-Mixer in image recognition tasks.
IGSD separates task-specific content channels in transformer components by comparing activation replacement with zero ablation.
problem Mechanistic interpretability of transformer components
method IGSD: paired-intervention framework for comparing activation replacement with zero ablation
result IGSD identifies an early-layer content channel in transformer components that standard importance methods underestimate.
Softmax is found ineffective for NL block, leading to improved performance.
problem Inefficiency of softmax in NL block for global context modeling.
method Empirical analysis and replacement of softmax with scaling factor.
result Improved performance on various datasets with reduced computational cost.
This paper finds the noise threshold for learning Gaussian mixture models equals channel capacity.
problem Learning Gaussian mixture models with noisy data.
method Bayesian formulation with uniformly distributed centers on a sphere, analyzing the large system limit.
result The maximal noise level σ2 for which GMM learning is as easy as labeled observations is the channel capacity. CRAUM-Net improves salient object detection with context and uncertainty modeling.
problem Accurate salient object detection with precise boundary delineation.
method Contextual Recursive Attention with Uncertainty Modeling, multi-scale context aggregation, attention mechanisms, edge-aware decoder, Monte Carlo Dropout.
result Superior performance in producing accurate and reliable saliency maps.
RoyalFlush system improves multi-speaker ASR in M2MeT challenge.
problem Improving multi-speaker automatic speech recognition in noisy environments.
method Front-end processing with WPE and beamforming, data augmentation, and fusion of two ASR models.
result 12.22% absolute CER reduction on validation set and 12.11% on test set compared to baseline.
Mind wandering (MW) is a ubiquitous phenomenon which reflects a shift in attention from task-related to task-unrelated thoughts. There is a need for intelligent interfaces that can reorient attention when MW is detected due to its detrimental effects on performance and productivity. In this paper, we propose a deep lea…
New framework uses MABs for better WLAN performance.
problem Maximizing enterprise WLAN performance with complex AP and station interactions.
method Empowered APs and stations with agents using Thompson sampling to learn optimal channel and AP selection.
result Adaptive framework using MABs outperforms static configurations in various scenarios.
Deep Q-Learning system for straddle options in volatile markets.
problem High computational costs and unstable performance in high-volatility markets.
method Attention mechanisms in Transformer-DDQN, novel reward function, and resistance level identification.
result Transformer-DDQN model exhibits lowest maximum drawdown and highest average return.
We propose a dynamic neighborhood aggregation (DNA) procedure guided by (multi-head) attention for representation learning on graphs. In contrast to current graph neural networks which follow a simple neighborhood aggregation scheme, our DNA procedure allows for a selective and node-adaptive aggregation of neighboring …
New approach uses SPG for semantic communication without a known channel model.
problem Designing efficient semantic communication systems without a known channel model.
method Applying Stochastic Policy Gradient (SPG) for reinforcement learning.
result Achieves comparable performance to model-aware approaches with a decreased convergence rate.