arXiv subjects

Di Wu

Publications and source records attributed to Di Wu.

At least 433 records · Page 24Linked to original sources

arXiv2024

On Leveraging Encoder-only Pre-trained Language Models for Effective Keyphrase Generation

This study addresses the application of encoder-only Pre-trained Language Models (PLMs) in keyphrase generation (KPG) amidst the broader availability of domain-tailored encoder-only models compared to encoder-decoder models. We investigate three core inquiries: (1) the efficacy of encoder-only PLMs in KPG, (2) optimal architectural decisions for employing encoder-only PLMs in KPG, and (3) a performance comparison between in-domain encoder-only and encoder-decoder PLMs across varied resource settings. Our findings, derived from extensive experimentation in two domains reveal that with encoder-only PLMs, although KPE with Conditional Random Fields slightly excels in identifying present keyphrases, the KPG formulation renders a broader spectrum of keyphrase predictions. Additionally, prefix-LM fine-tuning of encoder-only PLMs emerges as a strong and data-efficient strategy for KPG, outperforming general-domain seq2seq PLMs. We also identify a favorable parameter allocation towards model depth rather than width when employing encoder-decoder architectures initialized with encoder-only PLMs. The study sheds light on the potential of utilizing encoder-only PLMs for advancing KPG systems and provides a groundwork for future KPG methods. Our code and pre-trained checkpoints are released at https://github.com/uclanlp/DeepKPG.

cs.CL↗

arXiv2024

A Tutorial on Environment-Aware Communications via Channel Knowledge Map for 6G

Sixth-generation (6G) mobile communication networks are expected to have dense infrastructures, large antenna size, wide bandwidth, cost-effective hardware, diversified positioning methods, and enhanced intelligence. Such trends bring both new challenges and opportunities for the practical design of 6G. On one hand, acquiring channel state information (CSI) in real time for all wireless links becomes quite challenging in 6G. On the other hand, there would be numerous data sources in 6G containing high-quality location-tagged channel data, e.g., the estimated channels or beams between base station (BS) and user equipment (UE), making it possible to better learn the local wireless environment. By exploiting this new opportunity and for tackling the CSI acquisition challenge, there is a promising paradigm shift from the conventional environment-unaware communications to the new environment-aware communications based on the novel approach of channel knowledge map (CKM). This article aims to provide a comprehensive overview on environment-aware communications enabled by CKM to fully harness its benefits for 6G. First, the basic concept of CKM is presented, followed by the comparison of CKM with various existing channel inference techniques. Next, the main techniques for CKM construction are discussed, including both environment model-free and environment model-assisted approaches. Furthermore, a general framework is presented for the utilization of CKM to achieve environment-aware communications, followed by some typical CKM-aided communication scenarios. Finally, important open problems in CKM research are highlighted and potential solutions are discussed to inspire future work.

cs.IT↗

arXiv2024

Graph Attention-based Reinforcement Learning for Trajectory Design and Resource Assignment in Multi-UAV Assisted Communication

In the multiple unmanned aerial vehicle (UAV)- assisted downlink communication, it is challenging for UAV base stations (UAV BSs) to realize trajectory design and resource assignment in unknown environments. The cooperation and competition between UAV BSs in the communication network leads to a Markov game problem. Multi-agent reinforcement learning is a significant solution for the above decision-making. However, there are still many common issues, such as the instability of the system and low utilization of historical data, that limit its application. In this paper, a novel graph-attention multi-agent trust region (GA-MATR) reinforcement learning framework is proposed to solve the multi-UAV assisted communication problem. Graph recurrent network is introduced to process and analyze complex topology of the communication network, so as to extract useful information and patterns from observational information. The attention mechanism provides additional weighting for conveyed information, so that the critic network can accurately evaluate the value of behavior for UAV BSs. This provides more reliable feedback signals and helps the actor network update the strategy more effectively. Ablation simulations indicate that the proposed approach attains improved convergence over the baselines. UAV BSs learn the optimal communication strategies to achieve their maximum cumulative rewards. Additionally, multi-agent trust region method with monotonic convergence provides an estimated Nash equilibrium for the multi-UAV assisted communication Markov game.

cs.MA↗

arXiv2024

Analysis of Knowledge Tracing performance on synthesised student data

Knowledge Tracing (KT) aims to predict the future performance of students by tracking the development of their knowledge states. Despite all the recent progress made in this field, the application of KT models in education systems is still restricted from the data perspectives: 1) limited access to real life data due to data protection concerns, 2) lack of diversity in public datasets, 3) noises in benchmark datasets such as duplicate records. To resolve these problems, we simulated student data with three statistical strategies based on public datasets and tested their performance on two KT baselines. While we observe only minor performance improvement with additional synthetic data, our work shows that using only synthetic data for training can lead to similar performance as real data.

cs.CY↗

arXiv2024

Probabilistic Mobility Load Balancing for Multi-band 5G and Beyond Networks

The ever-increasing demand for data services and the proliferation of user equipment (UE) have resulted in a significant rise in the volume of mobile traffic. Moreover, in multi-band networks, non-uniform traffic distribution among different operational bands can lead to congestion, which can adversely impact the user's quality of experience. Load balancing is a critical aspect of network optimization, where it ensures that the traffic is evenly distributed among different bands, avoiding congestion and ensuring better user experience. Traditional load balancing approaches rely only on the band channel quality as a load indicator and to move UEs between bands, which disregards the UE's demands and the band resource, and hence, leading to a suboptimal balancing and utilization of resources. To address this challenge, we propose an event-based algorithm, in which we model the load balancing problem as a multi-objective stochastic optimization, and assign UEs to bands in a probabilistic manner. The goal is to evenly distribute traffic across available bands according to their resources, while maintaining minimal number of inter-frequency handovers to avoid the signaling overhead and the interruption time. Simulation results show that the proposed algorithm enhances the network's performance and outperforms traditional load balancing approaches in terms of throughput and interruption time.

cs.NI↗

arXiv2024

Beyond Shared Vocabulary: Increasing Representational Word Similarities across Languages for Multilingual Machine Translation

Using a vocabulary that is shared across languages is common practice in Multilingual Neural Machine Translation (MNMT). In addition to its simple design, shared tokens play an important role in positive knowledge transfer, assuming that shared tokens refer to similar meanings across languages. However, when word overlap is small, especially due to different writing systems, transfer is inhibited. In this paper, we define word-level information transfer pathways via word equivalence classes and rely on graph networks to fuse word embeddings across languages. Our experiments demonstrate the advantages of our approach: 1) embeddings of words with similar meanings are better aligned across languages, 2) our method achieves consistent BLEU improvements of up to 2.3 points for high- and low-resource MNMT, and 3) less than 1.0\% additional trainable parameters are required with a limited increase in computational costs, while inference time remains identical to the baseline. We release the codebase to the community.

cs.CL↗

arXiv2024

Kernel-based multi-marker tests of association based on the accelerated failure time model

Kernel-based multi-marker tests for survival outcomes use primarily the Cox model to adjust for covariates. The proportional hazards assumption made by the Cox model could be unrealistic, especially in the long-term follow-up. We develop a suite of novel multi-marker survival tests for genetic association based on the accelerated failure time model, which is a popular alternative to the Cox model due to its direct physical interpretation. The tests are based on the asymptotic distributions of their test statistics and are thus computationally efficient. The association tests can account for the heterogeneity of genetic effects across sub-populations/individuals to increase the power. All the new tests can deal with competing risks and left truncation. Moreover, we develop small-sample corrections to the tests to improve their accuracy under small samples. Extensive numerical experiments show that the new tests perform very well in various scenarios. An application to a genetic dataset of Alzheimer's disease illustrates the tests' practical utility.

stat.ME↗

arXiv2024

Hallucination Detection and Hallucination Mitigation: An Investigation

Large language models (LLMs), including ChatGPT, Bard, and Llama, have achieved remarkable successes over the last two years in a range of different applications. In spite of these successes, there exist concerns that limit the wide application of LLMs. A key problem is the problem of hallucination. Hallucination refers to the fact that in addition to correct responses, LLMs can also generate seemingly correct but factually incorrect responses. This report aims to present a comprehensive review of the current literature on both hallucination detection and hallucination mitigation. We hope that this report can serve as a good reference for both engineers and researchers who are interested in LLMs and applying them to real world tasks.

cs.CL↗

arXiv2024

Masked Modeling for Self-supervised Representation Learning on Vision and Beyond

As the deep learning revolution marches on, self-supervised learning has garnered increasing attention in recent years thanks to its remarkable representation learning ability and the low dependence on labeled data. Among these varied self-supervised techniques, masked modeling has emerged as a distinctive approach that involves predicting parts of the original data that are proportionally masked during training. This paradigm enables deep models to learn robust representations and has demonstrated exceptional performance in the context of computer vision, natural language processing, and other modalities. In this survey, we present a comprehensive review of the masked modeling framework and its methodology. We elaborate on the details of techniques within masked modeling, including diverse masking strategies, recovering targets, network architectures, and more. Then, we systematically investigate its wide-ranging applications across domains. Furthermore, we also explore the commonalities and differences between masked modeling methods in different fields. Toward the end of this paper, we conclude by discussing the limitations of current techniques and point out several potential avenues for advancing masked modeling research. A paper list project with this survey is available at \url{https://github.com/Lupin1998/Awesome-MIM}.

cs.CV↗

arXiv2024

On the Selection of Intermediate Length Representative Periods for Capacity Expansion

As the decarbonization of power systems accelerates, there has been increasing interest in capacity expansion models for their role in guiding this transition. Representative period selection is an important component of capacity expansion modeling, enabling computational tractability of optimization while ensuring fidelity between the representative periods and the full year. However, little attention has been devoted to selecting representative periods longer than a single day. This prevents the capacity expansion model from directly simulating interday energy sharing, which is of key importance as energy generation becomes more variable and storage more important. To this end, we propose a novel method for selecting representative periods of any length. The method is validated using a capacity expansion model and production cost model based on California's decarbonization goals. We demonstrate that the representative period length has a substantial impact in the results of the capacity expansion investment plan.

eess.SY↗

arXiv2024

EcoFed: Efficient Communication for DNN Partitioning-based Federated Learning

Efficiently running federated learning (FL) on resource-constrained devices is challenging since they are required to train computationally intensive deep neural networks (DNN) independently. DNN partitioning-based FL (DPFL) has been proposed as one mechanism to accelerate training where the layers of a DNN (or computation) are offloaded from the device to the server. However, this creates significant communication overheads since the intermediate activation and gradient need to be transferred between the device and the server during training. While current research reduces the communication introduced by DNN partitioning using local loss-based methods, we demonstrate that these methods are ineffective in improving the overall efficiency (communication overhead and training speed) of a DPFL system. This is because they suffer from accuracy degradation and ignore the communication costs incurred when transferring the activation from the device to the server. This article proposes EcoFed - a communication efficient framework for DPFL systems. EcoFed eliminates the transmission of the gradient by developing pre-trained initialization of the DNN model on the device for the first time. This reduces the accuracy degradation seen in local loss-based methods. In addition, EcoFed proposes a novel replay buffer mechanism and implements a quantization-based compression technique to reduce the transmission of the activation. It is experimentally demonstrated that EcoFed can reduce the communication cost by up to 133x and accelerate training by up to 21x when compared to classic FL. Compared to vanilla DPFL, EcoFed achieves a 16x communication reduction and 2.86x training time speed-up. EcoFed is available from https://github.com/blessonvar/EcoFed.

cs.DC↗

arXiv2023

A Split-and-Privatize Framework for Large Language Model Fine-Tuning

Fine-tuning is a prominent technique to adapt a pre-trained language model to downstream scenarios. In parameter-efficient fine-tuning, only a small subset of modules are trained over the downstream datasets, while leaving the rest of the pre-trained model frozen to save computation resources. In recent years, a popular productization form arises as Model-as-a-Service (MaaS), in which vendors provide abundant pre-trained language models, server resources and core functions, and customers can fine-tune, deploy and invoke their customized model by accessing the one-stop MaaS with their own private dataset. In this paper, we identify the model and data privacy leakage risks in MaaS fine-tuning, and propose a Split-and-Privatize (SAP) framework, which manage to mitigate the privacy issues by adapting the existing split learning architecture. The proposed SAP framework is sufficiently investigated by experiments, and the results indicate that it can enhance the empirical privacy by 62% at the cost of 1% model performance degradation on the Stanford Sentiment Treebank dataset.

cs.CL↗

arXiv2023

Model-independent search for the quasinormal modes of gravitational wave echoes

Postmerger gravitational wave echoes provide a unique opportunity to probe the near-horizon structure of astrophysical black holes, which may be modified due to nonperturbative quantum gravity phenomena. However, since the waveform is subject to large theoretical uncertainties, it is necessary to develop search methods that are less reliant on specific models for detecting echoes from observational data. A promising strategy is to identify the characteristic quasinormal modes (QNMs) associated with echoes, {\it in frequency space}, which complements existing searches of quasiperiodic pulses in time. In this study, we build upon our previous work targeting these modes by incorporating relative phase information to optimize the Bayesian search algorithm. Using a new phase-marginalized likelihood, the performance can be significantly improved for well-resolved QNMs. This enables an efficient search for QNMs of various shapes, utilizing a simple search template that is independent of specific models. To demonstrate the robustness of the search algorithm, we construct four complementary benchmarks for the echo waveform that span a diverse range of different theoretical possibilities for the near-horizon structure. We then validate our Bayesian search algorithms by injecting the benchmark models into different realizations of Gaussian noise. Using two types of phase-marginalized likelihoods, we find that the search algorithm can efficiently detect the corresponding QNMs. Therefore, our search strategy provides a concrete Bayesian and model-independent approach to "quantum black hole seismology."

gr-qc↗

arXiv2023

Neural Network Approximation for Pessimistic Offline Reinforcement Learning

Deep reinforcement learning (RL) has shown remarkable success in specific offline decision-making scenarios, yet its theoretical guarantees are still under development. Existing works on offline RL theory primarily emphasize a few trivial settings, such as linear MDP or general function approximation with strong assumptions and independent data, which lack guidance for practical use. The coupling of deep learning and Bellman residuals makes this problem challenging, in addition to the difficulty of data dependence. In this paper, we establish a non-asymptotic estimation error of pessimistic offline RL using general neural network approximation with $\mathcal{C}$-mixing data regarding the structure of networks, the dimension of datasets, and the concentrability of data coverage, under mild assumptions. Our result shows that the estimation error consists of two parts: the first converges to zero at a desired rate on the sample size with partially controllable concentrability, and the second becomes negligible if the residual constraint is tight. This result demonstrates the explicit efficiency of deep adversarial offline RL frameworks. We utilize the empirical process tool for $\mathcal{C}$-mixing sequences and the neural network approximation theory for the Hölder class to achieve this. We also develop methods to bound the Bellman estimation error caused by function approximation with empirical Bellman constraint perturbations. Additionally, we present a result that lessens the curse of dimensionality using data with low intrinsic dimensionality and function classes with low complexity. Our estimation provides valuable insights into the development of deep offline RL and guidance for algorithm model design.

cs.LG↗

arXiv2023

An Iterative Bidirectional Gradient Boosting Approach for CVR Baseline Estimation

This paper presents a novel Iterative Bidirectional Gradient Boosting Model (IBi-GBM) for estimating the baseline of Conservation Voltage Reduction (CVR) programs. In contrast to many existing methods, we treat CVR baseline estimation as a missing data retrieval problem. The approach involves dividing the load and its corresponding temperature profiles into three periods: pre-CVR, CVR, and post-CVR. To restore the missing load profile during the CVR period, the method employs a three-step process. First, a forward-pass GBM is executed using data from the pre-CVR period as inputs. Subsequently, a backward-pass GBM is applied using data from the post-CVR period. The two restored load profiles are reconciled, considering pre-calculated weights derived from forecasting accuracy, and only the leftmost and rightmost points are retained. The newly restored points are then included as inputs for the subsequent iteration. This iterative procedure continues until the original load data in the CVR period is fully restored. We develop IBi-GBM using actual smart meter and Supervisory Control and Data Acquisition (SCADA) data. Our results demonstrate that IBi-GBM exhibits robust performance across various data resolutions and in different seasons and outperforms existing methods by achieving a 1-2% reduction in normalized Root Mean Square Error (nRMSE).

eess.SY↗

arXiv2023

Traffic Signal Control Using Lightweight Transformers: An Offline-to-Online RL Approach

Efficient traffic signal control is critical for reducing traffic congestion and improving overall transportation efficiency. The dynamic nature of traffic flow has prompted researchers to explore Reinforcement Learning (RL) for traffic signal control (TSC). Compared with traditional methods, RL-based solutions have shown preferable performance. However, the application of RL-based traffic signal controllers in the real world is limited by the low sample efficiency and high computational requirements of these solutions. In this work, we propose DTLight, a simple yet powerful lightweight Decision Transformer-based TSC method that can learn policy from easily accessible offline datasets. DTLight novelly leverages knowledge distillation to learn a lightweight controller from a well-trained larger teacher model to reduce implementation computation. Additionally, it integrates adapter modules to mitigate the expenses associated with fine-tuning, which makes DTLight practical for online adaptation with minimal computation and only a few fine-tuning steps during real deployment. Moreover, DTLight is further enhanced to be more applicable to real-world TSC problems. Extensive experiments on synthetic and real-world scenarios show that DTLight pre-trained purely on offline datasets can outperform state-of-the-art online RL-based methods in most scenarios. Experiment results also show that online fine-tuning further improves the performance of DTLight by up to 42.6% over the best online RL baseline methods. In this work, we also introduce Datasets specifically designed for TSC with offline RL (referred to as DTRL). Our datasets and code are publicly available.

cs.LG↗

arXiv2023

Anomaly Detection for Scalable Task Grouping in Reinforcement Learning-based RAN Optimization

The use of learning-based methods for optimizing cellular radio access networks (RAN) has received increasing attention in recent years. This coincides with a rapid increase in the number of cell sites worldwide, driven largely by dramatic growth in cellular network traffic. Training and maintaining learned models that work well across a large number of cell sites has thus become a pertinent problem. This paper proposes a scalable framework for constructing a reinforcement learning policy bank that can perform RAN optimization across a large number of cell sites with varying traffic patterns. Central to our framework is a novel application of anomaly detection techniques to assess the compatibility between sites (tasks) and the policy bank. This allows our framework to intelligently identify when a policy can be reused for a task, and when a new policy needs to be trained and added to the policy bank. Our results show that our approach to compatibility assessment leads to an efficient use of computational resources, by allowing us to construct a performant policy bank without exhaustively training on all tasks, which makes it applicable under real-world constraints.

cs.LG↗

arXiv2023

Attend Who is Weak: Enhancing Graph Condensation via Cross-Free Adversarial Training

In this paper, we study the \textit{graph condensation} problem by compressing the large, complex graph into a concise, synthetic representation that preserves the most essential and discriminative information of structure and features. We seminally propose the concept of Shock Absorber (a type of perturbation) that enhances the robustness and stability of the original graphs against changes in an adversarial training fashion. Concretely, (I) we forcibly match the gradients between pre-selected graph neural networks (GNNs) trained on a synthetic, simplified graph and the original training graph at regularly spaced intervals. (II) Before each update synthetic graph point, a Shock Absorber serves as a gradient attacker to maximize the distance between the synthetic dataset and the original graph by selectively perturbing the parts that are underrepresented or insufficiently informative. We iteratively repeat the above two processes (I and II) in an adversarial training fashion to maintain the highly-informative context without losing correlation with the original dataset. More importantly, our shock absorber and the synthesized graph parallelly share the backward process in a free training manner. Compared to the original adversarial training, it introduces almost no additional time overhead. We validate our framework across 8 datasets (3 graph and 5 node classification datasets) and achieve prominent results: for example, on Cora, Citeseer and Ogbn-Arxiv, we can gain nearly 1.13% to 5.03% improvements compare with SOTA models. Moreover, our algorithm adds only about 0.2% to 2.2% additional time overhead over Flicker, Citeseer and Ogbn-Arxiv. Compared to the general adversarial training, our approach improves time efficiency by nearly 4-fold.

cs.LG↗