Inspired by this finding, we propose a novel replay-based method called proxy-based contrastive replay (PCR), which replaces anchor-to-sample pairs with anchor-to-proxy pairs in the contrastive-based loss to alleviate the phenomenon of forgetting.
Moreover, given a real-time constraint of one minute, the NIE-based method can solve IBM problems with up to hundreds of thousands of nodes, which is at least one order of magnitude larger than what can be solved by existing methods.
Particularly, a city-level correlation strategy is devised to attentively capture common patterns among cities, so as to transfer more relevant knowledge from more correlated cities.
We first present the problem formulation of DDCCMCKP, and then establish two benchmark sets.
Synthesis of digital artifacts conditioned on user prompts has become an important paradigm facilitating an explosion of use cases with generative AI.
This survey presents a critical overview of BFL, including its basic concepts, its relations to Bayesian learning in the context of FL, and a taxonomy of BFL from both Bayesian and federated perspectives.
To resolve this problem, this paper tries to learn the diverse policies from the history of state-action pairs under a non-Markovian environment, in which a policy dispersion scheme is designed for seeking diverse policy representation.
On the other hand, if the samples are too sparse, existing PINNs tend to overfit the near boundary region, leading to incorrect solution.
The potential of learned models for fundamental scientific research and discovery is drawing increasing attention.
We further propose Graph selective attention networks (SATs) to learn representations from the highly correlated node features identified and investigated by different SA mechanisms.
Being equipped with three modules (i. e., global user behavior encoder, local multi-channel encoder, and region-aware weighting strategy), MCMG is capable of capturing both fine- and coarse-grained sequential regularities as well as exploring the dynamic impact of multi-channel by differentiating the region check-in patterns.
Besides the "trade-off" relationship, they might be positively correlated with each other, that is, having a same-trend (win-win or lose-lose) relationship, which varies across different methods and datasets.
Recently, one critical issue looms large in the field of recommender systems -- there are no effective benchmarks for rigorous evaluation -- which consequently leads to unreproducible evaluation and unfair comparison.
Recently, neural implicit surfaces learning by volume rendering has become popular for multi-view reconstruction.
Granger causality is a commonly used method for uncovering information flow and dependencies in a time series.
Model robustness is vital for the reliable deployment of machine learning models in real-world applications.
We believe that this technical review can help to promote a sustainable development of AI R&D activities for the research community.
This paper is the first to address the shortcoming of today's methods via a novel neuroevolutionary multitasking (NuEMT) algorithm, designed to transfer information from a set of auxiliary tasks (of short episode length) to the target (full length) RL task at hand.
Multi-task Gaussian process (MTGP) is a well-known non-parametric Bayesian model for learning correlated tasks effectively by transferring knowledge across tasks.
In this study, novel physics-informed neural network (PINN) methods for coupling neighboring support points and their derivative terms which are obtained by automatic differentiation (AD), are proposed to allow efficient training with improved accuracy.
Adversarial examples in automatic speech recognition (ASR) are naturally sounded by humans yet capable of fooling well trained ASR models to transcribe incorrectly.
Until recently, the potential to transfer evolved skills across distinct optimization problem instances (or tasks) was seldom explored in evolutionary computation.
Current one-stage methods for visual grounding encode the language query as one holistic sentence embedding before fusion with visual feature.
The performance of machine learning algorithms heavily relies on the availability of a large amount of training data.
In the case of alternative splicing prediction, DCEN models mRNA transcript probabilities through its constituent splice junctions' energy values.
This paper thus proposes a new search paradigm, namely the multi-space evolutionary search, to enhance the existing evolutionary search methods for solving large-scale optimization problems.
Given the novel Conjoint Attention strategies, we then propose Graph conjoint attention networks (CATs) that can learn representations embedded with significant latent features deemed by the Conjoint Attentions.
In the context of solving differential equations, we are faced with the problem of finding globally optimum parameters of the network, instead of being concerned with out-of-sample generalization.
Under such settings, existing transfer evolutionary optimization frameworks grapple with simultaneously satisfying two important quality attributes, namely (1) scalability against a growing number of source tasks and (2) online learning agility against sparsity of relevant sources to the target task of interest.
This paper demonstrates a fatal vulnerability in natural language inference (NLI) and text classification systems.
For a learning task, Gaussian process (GP) is interested in learning the statistical relationship between inputs and outputs, since it offers not only the prediction mean but also the associated variability.
Motivated by this finding, we propose a new policy distillation loss with two terms: 1) a prescription gap maximization loss aiming at simultaneously maximizing the likelihood of the action selected by the teacher policy and the entropy over the remaining actions; 2) a corresponding Jacobian regularization loss that minimizes the magnitude of the gradient with respect to the input state.
While there are studies that seek to control high-level attributes (such as sentiment and topic) of generated text, there is still a lack of more precise control over its content at the word- and phrase-level.
The real-world data usually exhibits heterogeneous properties such as modalities, views, or resources, which brings some unique challenges wherein the key is Heterogeneous Representation Learning (HRL) termed in this paper.
Learned weights of models robust to such perturbations are previously found to be transferable across different tasks but this applies only if the model architecture for the source and target tasks is the same.
Existing defenses are effective under certain conditions such as a small size of the poison pattern, knowledge about the ratio of poisoned training samples or when a validated clean dataset is available.
Recent studies have revealed that neural network-based policies can be easily fooled by adversarial examples.
Gaussian process classification (GPC) provides a flexible and powerful statistical framework describing joint distributions over function space.
In this article, we provide and overview of what we consider to be some of the most pressing research questions facing the fields of artificial intelligence (AI) and computational intelligence (CI); with the latter focusing on algorithms that are inspired by various natural phenomena.
In particular, we propose a novel approach of sequential learning of smart contract vulnerabilities using machine learning --- long-short term memory (LSTM) --- that perpetually learns from an increasing number of contracts handled over time, leading to safer smart contracts.
Cryptography and Security
This paper devotes to investigating the methodological characteristics and performance of representative global and local scalable GPs including sparse approximations and local aggregations from four main perspectives: scalability, capability, controllability and robustness.
To improve the scalability, we first develop a variational sparse inference algorithm, named VSHGP, to handle large-scale datasets.
In order to scale standard Gaussian process (GP) regression to large-scale datasets, aggregation models employ factorized training process and then combine predictions from distributed experts.
A key challenge in multi-source transfer learning is to capture the diverse inter-domain similarities.
In this report, we suggest nine test problems for multi-task single-objective optimization (MTSOO), each of which consists of two single-objective optimization tasks that need to be solved simultaneously.
In this report, we suggest nine test problems for multi-task multi-objective optimization (MTMOO), each of which consists of two multiobjective optimization tasks that need to be solved simultaneously.
In this paper, we propose a co-evolutionary multi-task learning method that provides a synergy between multi-task learning and co-evolutionary algorithms to address dynamic time series prediction.
Evolutionary multitasking has recently emerged as a novel paradigm that enables the similarities and/or latent complementarities (if present) between distinct optimization tasks to be exploited in an autonomous manner simply by solving them together with a unified solution representation scheme.
Despite their encouraging results reported, the existing online AUC maximization algorithms often adopt simple online gradient descent approaches that fail to exploit the geometrical knowledge of the data observed during the online learning process, and thus could suffer from relatively larger regret.