AMI-Net+ tackles medical diagnosis from incomplete, imbalanced data.
problem Medical diagnosis from incomplete and imbalanced data.
method AMI-Net+ uses multi-instance neural network with embedding, multi-head attention, and gated attention-based pooling. It also employs focal loss and self-adaptive multi-instance pooling.
result AMI-Net+ outperforms state-of-the-art models on real-world medical datasets.
Proposes SAG-DBSCAN for clustering with self-adaptation.
problem Clustering analysis in data mining.
method Uses grey relational matrix and DBSCAN for clustering.
result Demonstrates superior performance compared to other methods.
Self-adaptive training improves deep learning robustness.
problem Improving deep learning performance on corrupted data.
method Dynamic correction of problematic labels using model predictions.
result Self-adaptive training significantly improves generalization over ERM under various levels of noise.
A new clustering algorithm fuses heat diffusion and turning angle for robustness.
problem Cluster similar elements in various fields.
method Combines heat diffusion and maximal turning angle for robust fission clustering.
result The SARFC algorithm outperforms other methods in clustering performance.
Self-adaptive PINNs improve accuracy in stiff PDEs.
problem Accurate numerical solution of stiff PDEs using neural networks.
method Adaptive weights applied to each training point individually, using a soft attention mechanism.
result SA-PINNs outperform other PINN algorithms in L2 error with fewer training epochs.
Paper proposes a new method for robust speaker verification.
problem Improving robustness in speaker verification systems.
method Combines soft VAD and self-adaptive VAD with DNN-based VAD.
result Significant improvement in verification performance in real-world environments.
Proposes EDESH-SA for better inventory management under uncertainty.
problem Inventory management under uncertainty.
method Ensemble Differential Evolution with simulation-based hybridization and self-adaptation.
result Improves financial performance and optimizes search spaces.
M-L2O adapts fast to new tasks by self-adapting during test-time.
problem L2O optimizers struggle with out-of-distribution tasks.
method Meta-training an L2O optimizer to adapt quickly to new tasks.
result M-L2O converges significantly faster than vanilla L2O with only 5 steps of adaptation.
Improves neural networks by adjusting labels to reduce overfitting to noisy data.
problem Reduces overfitting to mislabeled or non-representative samples in neural networks.
method Combines self-adaptive training with mixup to improve accuracy and robustness.
result Achieves state-of-the-art accuracy on image recognition datasets with label noise.
This work initiates a general study of learning and generalization without the i.i.d. assumption, starting from first principles. While the traditional approach to statistical learning theory typically relies on standard assumptions from probability theory (e.g., i.i.d. or stationary ergodic), in this work we are inter…
Probability Density Estimation (PDE) is a multivariate discrimination technique based on sampling signal and background densities defined by event samples from data or Monte-Carlo (MC) simulations in a multi-dimensional phase space. In this paper, we present a modification of the PDE method that uses a self-adapting bi…
Structure plays a key role in learning performance. In centralized computational systems, hyperparameter optimization and regularization techniques such as dropout are computational means to enhance learning performance by adjusting the deep hierarchical structure. However, in decentralized deep learning by the Interne…
Convolutional neural networks (CNNs) have achieved remarkable performance in many applications, especially in image recognition tasks. As a crucial component of CNNs, sub-sampling plays an important role for efficient training or invariance property, and max-pooling and arithmetic average-pooling are commonly used sub-…
Speech enhancement improved by adapting to unknown speakers without auxiliary signals.
problem Improving speech enhancement accuracy for unknown speakers.
method Adopting multi-task learning for speech enhancement and speaker identification, using multi-head self-attention.
result Achieved state-of-the-art performance and improved subjective quality.
Global catastrophe risk pools increase financial resilience by diversifying risk and including more countries.
problem Low- to middle-income countries rely heavily on foreign aid for recovery from extreme weather events, which is slow and uncertain.
method Developed a method to form global catastrophe risk pools that maximize risk diversification and select countries with low bilateral correlations or low shares in the pool risk.
result Global pooling increases risk diversification, lowers countries' shares in the pool risk, and increases the number of countries benefiting from risk pooling.
Paper presents a self-adaptive learning model for robust classification and regression.
problem Dealing with various datasets of different complexity.
method Combines DNDN and DSP, an end-to-end training approach with multiple randomly initialized softmax layers and adaptive soft pruning.
result The model demonstrates no performance loss compared with unpruned models and higher robustness over different data and feature distributions.
In most convolution neural networks (CNNs), downsampling hidden layers is adopted for increasing computation efficiency and the receptive field size. Such operation is commonly so-called pooling. Maximation and averaging over sliding windows (max/average pooling), and plain downsampling in the form of strided convoluti…
New image classifier uses hierarchical max-pooling with local pooling.
problem Improving image classification accuracy with variable spatial relationships.
method Introduces a hierarchical max-pooling model with additional local pooling for convolutional neural networks.
result Demonstrates improved performance in estimating image features.
Paper introduces a novel error measure for neural networks integrating statistical and information theory.
problem No single error measure is universally best for neural network training.
method Developed a novel error measure EExpAbs and integrated it into the Levenberg-Marquardt algorithm. result Self-adaptive, dynamic learning algorithm improves both model accuracy and training process.
EdgePool improves GNN performance by pooling edges, not nodes.
problem Lack of effective graph pooling methods in GNNs.
method Edge contraction pooling approach.
result EdgePool outperforms alternative pooling methods.
We seek to improve deep neural networks by generalizing the pooling operations that play a central role in current architectures. We pursue a careful exploration of approaches to allow pooling to learn and to adapt to complex and variable patterns. The two primary directions lie in (1) learning a pooling function via (…
Optimizes diversification in catastrophe risk pooling using asymptotic analysis.
problem Maximizing diversification benefit from catastrophic events in insurance pools.
method Asymptotic analysis to solve high-dimensional optimization problem.
result Derives an asymptotically optimal pool that approximates practical optimal pool.
The human brain is able to learn, generalize, and predict crossmodal stimuli. Learning by expectation fine-tunes crossmodal processing at different levels, thus enhancing our power of generalization and adaptation in highly dynamic environments. In this paper, we propose a deep neural architecture trained by using expe…
An efficient algorithm identifies labels from sparse pooled data.
problem Identify unknown labels from condensed measurements of items.
method Design an efficient algorithm based on novel pooling scheme.
result Resolves statistical-to-computational gap in minimum pools needed.
This paper investigates the impact of dark pools on price discovery (the efficiency of prices on stock exchanges to aggregate information). Assets are traded in either an exchange or a dark pool, with the dark pool offering better prices but lower execution rates. Informed traders receive noisy and heterogeneous signal…
This research simplifies lending pools in decentralized finance for better understanding and security.
problem Complexity and lack of executable models make lending pools hard to understand and predict.
method Developed a formal model to reflect common features of lending pools and proved general properties.
result Proved correct handling of funds and described vulnerabilities and attacks.
Develops a novel global pooling framework using optimal transport.
problem Sub-optimal performance in global pooling operations.
method Regularized Optimal Transport (ROT) for generalized global pooling.
result ROTP layers can improve performance in various machine learning scenarios.
We consider interactive algorithms in the pool-based setting, and in the stream-based setting. Interactive algorithms observe suggested elements (representing actions or queries), and interactively select some of them and receive responses. Pool-based algorithms can select elements at any order, while stream-based algo…
In this work we compute lower Lipschitz bounds of ℓp pooling operators for p=1,2,∞ as well as ℓp pooling operators preceded by half-rectification layers. These give sufficient conditions for the design of invertible neural network layers. Numerical experiments on MNIST and image patches confirm tha…
The paper introduces a pooling mechanism for graph CNNs using NMF.
problem Pooling in graph structured data for efficient computation.
method Non-negative matrix factorization for node pooling.
result The pooling mechanism improves graph classification performance.
ASAP improves graph pooling for hierarchical graph representations.
problem Pooling in graphs fails to effectively capture substructure or scale to large graphs.
method ASAP uses self-attention and modified GNN to capture node importance and learn sparse soft cluster assignments.
result Combining ASAP with GNN architectures leads to state-of-the-art results on graph classification benchmarks.
We propose a novel graph pooling operation using cliques as the unit pool. As this approach is purely topological, rather than featural, it is more readily interpretable, a better analogue to image coarsening than filtering or pruning techniques, and entirely nonparametric. The operation is implemented within graph con…
A new method pools graph vertex representations into a function space for better graph classification.
problem Pooling graph vertex representations for graph-centric tasks.
method Proposes a novel function space pooling method for graph neural networks.
result The proposed method generally outperforms existing pooling methods in graph classification.
HGP-SL pools and learns graph structure for hierarchical representation learning.
problem Graph pooling is overlooked in GNN models, limiting hierarchical representation learning.
method Integrates graph pooling and structure learning into a unified module.
result HGP-SL improves graph classification performance on benchmarks.
Proposes a graph pooling method leveraging node proximity for hierarchical graph representation learning.
problem Efficiently exploiting the geometry of graph data for hierarchical representation learning.
method Combines node proximity with kernel representation of topology and node features for adaptive node signal similarities evaluation.
result Achieves state-of-the-art performance on graph classification benchmark datasets.
Enhances financial time series forecasting with a multi-period learning framework.
problem Accurate financial time series forecasting requires considering both short-term and long-term trends.
method Proposes a Multi-period Learning Framework (MLF) with three modules: Inter-period Redundancy Filtering, Learnable Weighted-average Integration, and Multi-period self-Adaptive Patching.
result Improves financial time series forecasting accuracy and efficiency.
EarnMore uses masked stock representations to train RL agents for customizable stock pools efficiently.
problem Training RL agents for customizable stock pools (CSPs) is computationally expensive and unstable.
method EarnMore introduces a mechanism to mask out stocks outside the target pool, learns meaningful stock representations, and uses a re-weighting mechanism to focus on favorable stocks.
result EarnMore significantly outperforms state-of-the-art baselines in profit metrics with over 40% improvement.
Global pooling, such as max- or sum-pooling, is one of the key ingredients in deep neural networks used for processing images, texts, graphs and other types of structured data. Based on the recent DeepSets architecture proposed by Zaheer et al. (NIPS 2017), we introduce a Set Aggregation Network (SAN) as an alternative…
Graph neural networks, which generalize deep neural network models to graph structured data, have attracted increasing attention in recent years. They usually learn node representations by transforming, propagating and aggregating node features and have been proven to improve the performance of many graph related tasks…
Study characterizes Uniswap v3 liquidity pools using transaction graphs and identifies ideal trading conditions.
problem Computational expense in analyzing the full Uniswap v3 ecosystem.
method Extracted and analyzed a sub-universe of liquidity pools, using transaction graphs and graph2vec algorithm.
result Identified seven clusters of liquidity takers with similar trading preferences and introduced an ideal crypto law.
Optimal rebalancing strategy improves AMM pool performance by 25%.
problem Optimizing the sequence of weights in dynamic AMM pools to minimize rebalancing costs.
method Using optimal interpolation and a cheap-to-compute approximation to achieve nearly optimal rebalancing.
result Approximately-optimal weight changes lead to significant increases in pool performance (up to 25%) under various conditions.
High-fee pools attract more liquidity but execute less volume; low-fee pools have more stable LPs.
problem Optimal liquidity supply and execution on decentralized exchanges with fixed gas costs.
method Analysis of Uniswap data to compare high- and low-fee pools.
result Fragmented liquidity leads to more LPs and competition, improving overall market efficiency.
Study optimal liquidation strategies in lit and dark pools with and without regulation.
problem Optimal liquidation strategies in dark and lit pools with execution uncertainty.
method Design optimal make-take fee policies, solve HJB-Fokker-Planck systems, use BSDEs.
result Explicit solutions for optimal strategies in both competitive and regulated markets.
SpaPool combines dense and sparse techniques for efficient graph pooling.
problem Efficiently processing large graphs in graph neural networks.
method Adaptive clustering of graph vertices into clusters.
result SpaPool outperforms existing methods on small-scale graphs.
Graph pooling method uses GNN to cluster graphs efficiently.
problem Efficiently cluster graphs for graph pooling.
method Formulates a continuous relaxation of minCUT, trains GNN to minimize it.
result GNN-based clustering learns fast and performs well.
This research improves capital efficiency and impermanent loss in cryptocurrency markets using multi-token trading pools.
problem Poor impermanent loss and capital efficiency in automated market makers.
method Analysis and construction of a multi-token token proactive market maker (MPMM).
result MPMM shows better impermanent loss and capital efficiency than comparable market makers.
Study on pooled annuity funds and how initial savings affect income stability.
problem Analyzing the stability of income payments in pooled annuity funds.
method Examining the influence of initial savings on income fluctuations and developing a criterion for pooling funds.
result Identification of a term, the 'implied number of homogeneous members', linking initial savings to income fluctuations.
We propose a max-pooling based loss function for training Long Short-Term Memory (LSTM) networks for small-footprint keyword spotting (KWS), with low CPU, memory, and latency requirements. The max-pooling loss training can be further guided by initializing with a cross-entropy loss trained network. A posterior smoothin…