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.
Paper proposes ADC framework to reduce ViT SL training communication overhead.
GOBO compresses 99.9% of BERT model parameters to 3 bits, improving inference efficiency.
This paper offers an overview of neural network compression techniques.
End-to-end automatic speech recognition (ASR) models are increasingly large and complex to achieve the best possible accuracy. In this paper, we build an AutoML system that uses reinforcement learning (RL) to optimize the per-layer compression ratios when applied to a state-of-the-art attention based end-to-end ASR mod…
Proposes ACLAE-DT for unsupervised anomaly detection in multivariate time series.
Many attempts have been done to extend the great success of convolutional neural networks (CNNs) achieved on high-end GPU servers to portable devices such as smart phones. Providing compression and acceleration service of deep learning models on the cloud is therefore of significance and is attractive for end users. Ho…
Global Memory Augmentation (GMAT) improves Transformer performance on long documents.
Deep neural network models have recently draw lots of attention, as it consistently produce impressive results in many computer vision tasks such as image classification, object detection, etc. However, interpreting such model and show the reason why it performs quite well becomes a challenging question. In this paper,…
RocketStack integrates predictions from multiple base learners using a recursive stacking architecture up to ten levels.
Attention-based models have recently shown great performance on a range of tasks, such as speech recognition, machine translation, and image captioning due to their ability to summarize relevant information that expands through the entire length of an input sequence. In this paper, we analyze the usage of attention mec…
ABC learns context-aware representations for clustering.
AGBoost uses attention weights to improve GBM for regression problems.
Graph Neural Networks (GNNs) are powerful to learn the representation of graph-structured data. Most of the GNNs use the message-passing scheme, where the embedding of a node is iteratively updated by aggregating the information of its neighbors. To achieve a better expressive capability of node influences, attention m…
Mathematical study shows post-hoc explanations are better than attention weights alone.
Sequence-to-sequence models, such as attention-based models in automatic speech recognition (ASR), are typically trained to optimize the cross-entropy criterion which corresponds to improving the log-likelihood of the data. However, system performance is usually measured in terms of word error rate (WER), not log-likel…
Attention-based GNNs can't prevent oversmoothing, leading to homogeneous node representations.
Proposes a novel node embedding framework for graphs using Fisher Information.
LARF improves random forests with attention mechanisms and contamination models.
Hybrid model predicts flow and pressure in water systems.
The recent proliferation of knowledge graphs (KGs) coupled with incomplete or partial information, in the form of missing relations (links) between entities, has fueled a lot of research on knowledge base completion (also known as relation prediction). Several recent works suggest that convolutional neural network (CNN…
Network embedding represents nodes in a continuous vector space and preserves structure information from the Network. Existing methods usually adopt a "one-size-fits-all" approach when concerning multi-scale structure information, such as first- and second-order proximity of nodes, ignoring the fact that different scal…
Models use embeddings and attention for better claim severity prediction.
Improves key instance detection in MIL models by using neural network inversion with sparseness constraint.
This paper introduces new attention-based convolutional neural networks for selecting bands from hyperspectral images. The proposed approach re-uses convolutional activations at different depths, identifying the most informative regions of the spectrum with the help of gating mechanisms. Our attention techniques are mo…
New methods improve integration of external LMs with AED models.
This paper presents our system details and results of participation in the RDoC Tasks of BioNLP-OST 2019. Research Domain Criteria (RDoC) construct is a multi-dimensional and broad framework to describe mental health disorders by combining knowledge from genomics to behaviour. Non-availability of RDoC labelled dataset …
Neural machine translation (NMT) systems have been shown to give undesirable translation when a small change is made in the source sentence. In this paper, we study the behaviour of NMT systems when multiple changes are made to the source sentence. In particular, we ask the following question "Is it possible for an NMT…
Text segmentation plays an important role in various Natural Language Processing (NLP) tasks like summarization, context understanding, document indexing and document noise removal. Previous methods for this task require manual feature engineering, huge memory requirements and large execution times. To the best of our …
Proposes new methods for interpreting document classification models.
Multiple instance learning (MIL) is a variation of supervised learning where a single class label is assigned to a bag of instances. In this paper, we state the MIL problem as learning the Bernoulli distribution of the bag label where the bag label probability is fully parameterized by neural networks. Furthermore, we …
Objective: To compare different deep learning architectures for predicting the risk of readmission within 30 days of discharge from the intensive care unit (ICU). The interpretability of attention-based models is leveraged to describe patients-at-risk. Methods: Several deep learning architectures making use of attentio…
We present an attention-based ranking framework for learning to order sentences given a paragraph. Our framework is built on a bidirectional sentence encoder and a self-attention based transformer network to obtain an input order invariant representation of paragraphs. Moreover, it allows seamless training using a vari…
In reinforcement learning algorithms, it is a common practice to account for only a single view of the environment to make the desired decisions; however, utilizing multiple views of the environment can help to promote the learning of complicated policies. Since the views may frequently suffer from partial observabilit…
Analyzes how BPE tokenisation affects corpus statistics and model entropy in transformer models.
Catastrophic forgetting/interference is a critical problem for lifelong learning machines, which impedes the agents from maintaining their previously learned knowledge while learning new tasks. Neural networks, in particular, suffer plenty from the catastrophic forgetting phenomenon. Recently there has been several eff…
Study compares deep learning models for traffic forecasting, highlighting graph elements' impact.
Image super-resolution is a challenging task and has attracted increasing attention in research and industrial communities. In this paper, we propose a novel end-to-end Attention-based DenseNet with Residual Deconvolution named as ADRD. In our ADRD, a weighted dense block, in which the current layer receives weighted f…
Improved hyperparameter optimization using simplified Transformer blocks.
Study improves stock price prediction using advanced ML models.
Flexible framework compresses models using LC algorithm.
Reduces multiclass and regression compression schemes to binary ones.
ResGCN detects anomalies in attributed networks by capturing sparsity and nonlinearity.
In line with recent advances in neural drug design and sensitivity prediction, we propose a novel architecture for interpretable prediction of anticancer compound sensitivity using a multimodal attention-based convolutional encoder. Our model is based on the three key pillars of drug sensitivity: compounds' structure i…
Proposes a link between randomness and compression in deep learning.
Out-of-vocabulary word translation is a major problem for the translation of low-resource languages that suffer from a lack of parallel training data. This paper evaluates the contributions of target-language context models towards the translation of OOV words, specifically in those cases where OOV translations are der…
New neural network improves audio classification accuracy.
In this paper, we propose a refined multi-stage multi-task training strategy to improve the performance of online attention-based encoder-decoder (AED) models. A three-stage training based on three levels of architectural granularity namely, character encoder, byte pair encoding (BPE) based encoder, and attention decod…
Paper introduces a new adaptive gradient method with gradient compression for distributed training.