Edge computing is a rapidly developing research area known for its ability to reduce latency and improve energy efficiency, and it also has a potential for green computing. Many geographically distributed edge servers...
详细信息
Traditional methods for detecting rumors on social media primarily focus on analyzing textual content, often struggling to capture the complexity of online interactions. Recent research has shifted towards leveraging ...
详细信息
Edge caching presents a promising avenue for mitigating backbone network congestion by strategically caching frequently accessed content at the network periphery. As most current edge caching solutions are designed fo...
详细信息
Automatic evaluation of hashtag recommendation models is a fundamental task in Twitter. In the traditional evaluation methods, the recommended hashtags from an algorithm are first compared with the ground truth hashta...
详细信息
Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and testing data by adapting a given model w.r.t. any testing sample. This task is particularly important when the test environ...
详细信息
Test-time adaptation (TTA) seeks to tackle potential distribution shifts between training and testing data by adapting a given model w.r.t. any testing sample. This task is particularly important when the test environment changes frequently. Although some recent attempts have been made to handle this task, we still face two key challenges: 1) prior methods have to perform backpropagation for each test sample, resulting in unbearable optimization costs to many applications;2) while existing TTA solutions can significantly improve the test performance on out-of-distribution data, they often suffer from severe performance degradation on in-distribution data after TTA (known as catastrophic forgetting). To this end, we have proposed an Efficient Anti-Forgetting Test-Time Adaptation (EATA) method which develops an active sample selection criterion to identify reliable and non-redundant samples for test-time entropy minimization. To alleviate forgetting, EATA introduces a Fisher regularizer estimated from test samples to constrain important model parameters from drastic changes. However, in EATA, the adopted entropy loss consistently assigns higher confidence to predictions even when the samples are underlying uncertain, leading to overconfident predictions that underestimate the data uncertainty. To tackle this, we further propose EATA with Calibration (EATA-C) to separately exploit the reducible model uncertainty and the inherent data uncertainty for calibrated TTA. Specifically, we compare the divergence between predictions from the full network and its sub-networks to measure the reducible model uncertainty, on which we propose a test-time uncertainty reduction strategy with divergence minimization loss to encourage consistent predictions instead of overconfident ones. To further re-calibrate predicting confidence on different samples, we utilize the disagreement among predicted labels as an indicator of the data uncertainty. Based on this, we devise a min-max entropy
Within the realm of multimodal neural machine translation(MNMT),addressing the challenge of seamlessly integrating textual data with corresponding image data to enhance translation accuracy has become a pressing *** s...
详细信息
Within the realm of multimodal neural machine translation(MNMT),addressing the challenge of seamlessly integrating textual data with corresponding image data to enhance translation accuracy has become a pressing *** saw that discrepancies between textual content and associated images can lead to visual noise,potentially diverting the model’s focus away from the textual data and so affecting the translation’s comprehensive *** solve this visual noise problem,we propose an innovative KDNR-MNMT *** combines the knowledge distillation technique with an anti-noise interaction mechanism,which makes full use of the synthesized graphic knowledge and local image interaction masks,aiming to extract more effective visual ***,the KDNR-MNMT model adopts a multimodal adaptive gating fusion strategy to enhance the constructive interaction of different modal *** integrating a perceptual attention mechanism,which uses cross-modal interaction cues within the Transformer framework,our approach notably enhances the quality of machine translation *** confirmthemodel’s performance,we carried out extensive testing and assessment on the extensively utilized Multi30K *** outcomes of our experiments prove substantial enhancements in our model’s BLEU and METEOR scores,with respective increases of 0.78 and 0.99 points over prevailing *** accomplishment affirms the potency of our strategy for mitigating visual interference and heralds groundbreaking advancements within themultimodal NMT domain,further propelling the evolution of this scholarly pursuit.
A geometric intrinsic pre-processing algorithm(GPA for short)for solving largescale discrete mathematical-physical PDE in 2-D and 3-D case has been presented by Sun(in 2022–2023).Different from traditional preconditi...
详细信息
A geometric intrinsic pre-processing algorithm(GPA for short)for solving largescale discrete mathematical-physical PDE in 2-D and 3-D case has been presented by Sun(in 2022–2023).Different from traditional preconditioning,the authors apply the intrinsic geometric invariance,the Grid matrix G and the discrete PDE mass matrix B,stiff matrix A satisfies commutative operator BG=GB and AG=GA,where G satisfies G^(m)=I,m<parallelism of geometric mesh pre-transformation is mainly proportional to the number of faces of polyhedron”is obtained through research,and it is further found that“commutative of grid mesh matrix and mass matrix is an important basis for the feasibility and reliability of GPA algorithm”.
Predicting stable crystal structures for complex systems that involve multiple elements or a large number of atoms presents a formidable challenge in computational materials science. A recent study presents an efficie...
Algorithmic versions of the Lovász Local Lemma (ALLLs), or rather, the Moser-Tardos algorithm and its variants, are impactful in both theory and practice. In this paper, we take the first step towards the goal of...
Demand response has recently become an essential means for businesses to reduce production costs in industrial ***,the current industrial chain structure has also become increasingly complex,forming new characteristic...
详细信息
Demand response has recently become an essential means for businesses to reduce production costs in industrial ***,the current industrial chain structure has also become increasingly complex,forming new characteristics of multiplex networked industrial *** in real-time electricity prices in demand response propagate through the coupling and cascading relationships within and among these network layers,resulting in negative impacts on the overall energy management ***,existing demand response methods based on reinforcement learning typically focus only on individual agents without considering the influence of dynamic factors on intra and inter-network *** paper proposes a Layered Temporal Spatial Graph Attention(LTSGA)reinforcement learning algorithm suitable for demand response in multiplex networked industrial chains to address this *** algorithm first uses Long Short-Term Memory(LSTM)to learn the dynamic temporal characteristics of electricity prices for ***,LTSGA incorporates a layered spatial graph attention model to evaluate the impact of dynamic factors on the complex multiplex networked industrial chain *** demonstrate that the proposed LTSGA approach effectively characterizes the influence of dynamic factors on intra-and inter-network relationships within the multiplex industrial chain,enhancing convergence speed and algorithm performance compared with existing state-of-the-art algorithms.
暂无评论