Quaternion self-attention reduces computational cost and improves performance.
problem Existing quaternion self-attention increases computational cost and diverges attention distributions.
method Proposes a shared-score quaternion self-attention mechanism.
result Reduces score-computation multiplications by 75% and softmax operations from four to one.
New method uses shared attention for multi-task time series forecasting.
problem Insufficient training instances in single-task forecasting.
method Self-attention based sharing schemes across multiple tasks.
result Outperforms state-of-the-art single-task forecasting baselines and RNN-based multi-task forecasting method.
This work proposes a collaborative multi-head attention layer to reduce model size without sacrificing accuracy.
problem Over-parameterization in transformer models trained with large datasets.
method Proposes a collaborative multi-head attention layer that shares key/query projections.
result Reduction in model size by 4 for same accuracy and speed.
Bayesian neural networks improve knowledge sharing across networks.
problem Improving knowledge sharing between neural networks.
method Application of Bayesian interpretations to neural networks for feature sharing.
result Enhanced feature sharing across networks.
DAF uses attention sharing to adapt forecasts from abundant to scarce data.
problem Limited data for time series forecasting.
method Attention-based shared module and domain discriminator for domain adaptation.
result DAF outperforms state-of-the-art methods on various domains.
Reinforcement learning in multi-agent scenarios is important for real-world applications but presents challenges beyond those seen in single-agent settings. We present an actor-critic algorithm that trains decentralized policies in multi-agent settings, using centrally computed critics that share an attention mechanism…
We propose multi-way, multilingual neural machine translation. The proposed approach enables a single neural translation model to translate between multiple languages, with a number of parameters that grows only linearly with the number of languages. This is made possible by having a single attention mechanism that is …
The prevalence of social media has made information sharing possible across the globe. The downside, unfortunately, is the wide spread of misinformation. Methods applied in most previous rumor classifiers give an equal weight, or attention, to words in the microblog, and do not take the context beyond microblog content…
Mathematical framework for understanding attention in neural networks.
problem Lack of theoretical understanding of attention in neural networks.
method Proposes a measure-theoretic model of attention and interprets self-attention as a system of self-interacting particles.
result Shows that attention is Lipschitz-continuous under suitable assumptions.
Introduces Causal Energy Minimization to understand Transformer layers.
problem Empirical parameterization of Transformer blocks remains largely unexplored.
method Causal Energy Minimization framework that recasts Transformer layers as optimization steps on conditional energy functions.
result Identifies design space for Transformer layers including weight sharing and energy-based interpretations.
Multi-task learning shares information between related tasks, sometimes reducing the number of parameters required. State-of-the-art results across multiple natural language understanding tasks in the GLUE benchmark have previously used transfer from a single large task: unsupervised pre-training with BERT, where a sep…
Most companies utilize demographic information to develop their strategy in a market. However, such information is not available to most retail companies. Several studies have been conducted to predict the demographic attributes of users from their transaction histories, but they have some limitations. First, they focu…
This paper investigates weight-sharing in NAS, revealing its impact and providing solutions.
problem Reducing the time and computational cost of training neural networks.
method Comprehensive experiments on weight-sharing in NAS, analyzing variance and interference.
result Properly reducing weight sharing can reduce variance and improve model performance.
Paper proposes deep learning model for dynamic stock repurchase forecasting.
problem Complex temporal dependencies in corporate financial conditions.
method Hybrid Temporal Convolutional Network (TCN) and Attention-based LSTM.
result Model significantly outperforms static baselines in stock repurchase forecasting.
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.
Extends inf-convolution to countable risk measures for risk sharing.
problem Limited inf-convolution theory to finite sets of risk measures.
method Extends inf-convolution to countable sets, investigates properties and results.
result Generalizes known properties and results to countable case.
In a Markovian stochastic volatility model, we consider financial agents whose investment criteria are modelled by forward exponential performance processes. The problem of contingent claim indifference valuation is first addressed and a number of properties are proved and discussed. Special attention is given to the c…
Recommender systems (RS), which have been an essential part in a wide range of applications, can be formulated as a matrix completion (MC) problem. To boost the performance of MC, matrix completion with side information, called inductive matrix completion (IMC), was further proposed. In real applications, the factorize…
Time series prediction with deep learning methods, especially long short-term memory neural networks (LSTMs), have scored significant achievements in recent years. Despite the fact that the LSTMs can help to capture long-term dependencies, its ability to pay different degree of attention on sub-window feature within mu…
3D Axial-Attention improves lung nodule classification accuracy.
problem Limited 3D attention in existing methods.
method Proposes 3D Axial-Attention network with 3D positional encoding.
result 3D Axial-Attention achieves state-of-the-art performance.
InGRA models for efficient Granger causality learning in multivariate time series.
problem Efficiently modeling Granger causality in large-scale multivariate time series data.
method Inductive GRanger causal modeling (InGRA) framework with prototypical Granger causal attention.
result InGRA detects common causal structures and infers Granger causal structures for new individuals.
This paper improves transportation efficiency by teaching automated vehicles to cooperate.
problem Improving efficiency and safety of transportation systems with automated vehicles.
method Multi-agent graph reinforcement learning with attention mechanism.
result Automated vehicles can achieve better performance when learning to cooperate with each other.
This paper describes the participation of Amobee in the shared sentiment analysis task at SemEval 2018. We participated in all the English sub-tasks and the Spanish valence tasks. Our system consists of three parts: training task-specific word embeddings, training a model consisting of gated-recurrent-units (GRU) with …
Sharing knowledge between tasks is vital for efficient learning in a multi-task setting. However, most research so far has focused on the easier case where knowledge transfer is not harmful, i.e., where knowledge from one task cannot negatively impact the performance on another task. In contrast, we present an approach…
In recent years, dock-less shared bikes have been widely spread across many cities in China and facilitate people's lives. However, at the same time, it also raises many problems about dock-less shared bike management due to the mismatching between demands and real distribution of bikes. Before deploying dock-less shar…
LieTransformer extends self-attention to Lie groups for improved deep learning tasks.
problem Improving deep learning performance through group equivariant self-attention.
method LieSelfAttention layers that are equivariant to arbitrary Lie groups and their discrete subgroups.
result Competitive experimental results on various tasks.
NeoMLP improves neural fields by adding self-attention for better downstream tasks.
problem Complexity and lack of conditioning mechanisms in neural fields.
method Transformed MLP into NeoMLP with self-attention and weight-sharing.
result NeoMLP outperforms state-of-the-art methods in downstream tasks.
Study compares deep learning models for traffic forecasting, highlighting graph elements' impact.
problem Challenges in forecasting spatial-temporal traffic patterns.
method In-depth comparative study of four deep neural network models with different basic elements.
result Graph attention improves long-term predictions in traffic forecasting models.
DAGR improves navigation by refining goal representations conditioned on the current state.
problem Goal-conditioned reinforcement learning lacks state awareness, leading to inefficient policy recovery.
method DAGR refines static goal embeddings into state-conditioned ones using gated cross-attention with a state-goal discrepancy map.
result DAGR improves navigation tasks on OGBench, matching or outperforming base methods.
Attention improves edge prediction in e-commerce graphs.
problem Predicting edges in graphs from node attributes in e-commerce.
method Used attention mechanism in simple feedforward networks, derived analytically tractable model AttEST.
result Attention network outperforms LSTM architectures by over 20% on F-1 score.
Sensors are an integral part of modern Internet of Things (IoT) applications. There is a critical need for the analysis of heterogeneous multivariate temporal data obtained from the individual sensors of these systems. In this paper we particularly focus on the problem of the scarce amount of training data available pe…
A new method for efficient neural network fine-tuning using queryable low-rank update atoms.
problem Rigidity of static low-rank adaptation methods when input and depth-wise computation vary.
method A shared queryable memory of low-rank update atoms, allowing dynamic and context-sensitive adaptation.
result Improves final test performance and training stability compared to standard low-rank adaptation.
The use of automatic methods, often referred to as Neural Architecture Search (NAS), in designing neural network architectures has recently drawn considerable attention. In this work, we present an efficient NAS approach, named HM- NAS, that generalizes existing weight sharing based NAS approaches. Existing weight shar…
Transformers can approximate any sequence-to-sequence function, surprising given their complexity.
problem Understanding the expressive power of Transformer models for sequence-to-sequence functions.
method Established that Transformers are universal approximators of continuous permutation equivariant sequence-to-sequence functions with compact support, and extended this to arbitrary functions using positional encodings.
result Transformers are universal approximators of arbitrary continuous sequence-to-sequence functions on a compact domain.
CDAM improves attention maps for ViTs, making them more class-sensitive.
problem Existing attention maps in ViTs lack class sensitivity.
method Class-discriminative attention maps (CDAM) that scale attention scores by class relevance.
result CDAM provides more class-sensitive explanations than existing methods.
We present a memory augmented neural network for natural language understanding: Neural Semantic Encoders. NSE is equipped with a novel memory update rule and has a variable sized encoding memory that evolves over time and maintains the understanding of input sequences through read}, compose and write operations. NSE c…
HAMN combines CF models to improve drug repositioning.
problem Efficient drug repositioning with cold start problem.
method Hybrid Attentional Memory Network (HAMN) integrating memory and attention mechanisms.
result HAMN outperforms other models in drug repositioning tasks.
A transformer model improves spell correction with hierarchical attention.
problem Improving spell correction accuracy and speed.
method Multi encoder-single decoder transformer architecture with hierarchical attention.
result Significant improvement in CER, WER, and SER error rates.
We investigated the training of a shared model for both text-to-speech (TTS) and voice conversion (VC) tasks. We propose using an extended model architecture of Tacotron, that is a multi-source sequence-to-sequence model with a dual attention mechanism as the shared model for both the TTS and VC tasks. This model can a…
Secure social recommendation framework using secret sharing.
problem Privacy concerns and reluctance to share social data in recommender systems.
method Secret Sharing based Matrix Multiplication (SSMM) protocol for secure data sharing and collaborative recommendation.
result SeSoRec framework improves recommendation performance and is secure.
Cross-domain sentiment classification (CDSC) is an importance task in domain adaptation and sentiment classification. Due to the domain discrepancy, a sentiment classifier trained on source domain data may not works well on target domain data. In recent years, many researchers have used deep neural network models for c…
Proposes MANE for multi-view network embedding, improving node representations.
problem Learning low-dimensional representations from multiple views of networks.
method MANE combines diversity and collaboration, including second-order collaboration, and attention-based extension MANE+.
result MANE+ outperforms state-of-the-art approaches on real-world multi-view networks.
Attention mechanism combines bottom-up and top-down signals in neural networks.
problem Combining robust perception with bottom-up and top-down signals.
method Attention mechanism over modulated recurrent neural networks.
result Bidirectional information flow leads to improved performance in various tasks.
Shared workspace improves neural module coordination in deep learning.
problem Pairwise interactions in deep learning models lack global coordination.
method Introduce a shared global workspace with bandwidth limitations among neural modules.
result Capacity limitations encourage specialization and synchronization.
Paper proposes AoA, a new adversarial attack method that significantly increases transferability.
problem Developing universal adversarial attacks on deep neural networks.
method AoA attacks the semantic property of attention in DNNs, enhancing transferability by altering the loss function.
result AoA generates adversarial samples that defeat 13 well-trained DNNs, achieving over 85% error rate.
Enhanced deep learning model predicts stock price movement using LOB data.
problem Challenges in predicting stock price movement from high-dimensional, volatile LOB data.
method Siamese architecture with multi-head attention and LSTM modules.
result Significant improvement in stock price prediction performance over strong baselines.
The Hype Index measures media attention to equities using NLP.
problem Quantifying media attention to equities for volatility analysis.
method Constructs News Count-Based and Capitalization Adjusted Hype Indices using NLP.
result The Hype Index family provides valuable tools for stock volatility analysis.
Federated learning interprets temporal dynamics across clients with graph attention.
problem Interpreting temporal patterns across decentralized, heterogeneous systems with nonlinear dynamics.
method Graph Attention Network for learning state transition models over latent states communicated between clients.
result First interpretable characterization of cross-client temporal interdependencies in decentralized nonlinear systems.