arXiv subjects

Deqing Wang

Publications and source records attributed to Deqing Wang.

At least 55 records · Page 3Linked to original sources

arXiv2024

Adaptive Taxonomy Learning and Historical Patterns Modelling for Patent Classification

Patent classification aims to assign multiple International Patent Classification (IPC) codes to a given patent. Recent methods for automatically classifying patents mainly focus on analyzing the text descriptions of patents. However, apart from the texts, each patent is also associated with some assignees, and the knowledge of their applied patents is often valuable for classification. Furthermore, the hierarchical taxonomy formulated by the IPC system provides important contextual information and enables models to leverage the correlations between IPC codes for more accurate classification. However, existing methods fail to incorporate the above aspects. In this paper, we propose an integrated framework that comprehensively considers the information on patents for patent classification. To be specific, we first present an IPC codes correlations learning module to derive their semantic representations via adaptively passing and aggregating messages within the same level and across different levels along the hierarchical taxonomy. Moreover, we design a historical application patterns learning component to incorporate the corresponding assignee's previous patents by a dual channel aggregation mechanism. Finally, we combine the contextual information of patent texts that contains the semantics of IPC codes, and assignees' sequential preferences to make predictions. Experiments on real-world datasets demonstrate the superiority of our approach over the existing methods. Besides, we present the model's ability to capture the temporal patterns of assignees and the semantic dependencies among IPC codes.

cs.AI↗

arXiv2024

MoRA: High-Rank Updating for Parameter-Efficient Fine-Tuning

Low-rank adaptation is a popular parameter-efficient fine-tuning method for large language models. In this paper, we analyze the impact of low-rank updating, as implemented in LoRA. Our findings suggest that the low-rank updating mechanism may limit the ability of LLMs to effectively learn and memorize new knowledge. Inspired by this observation, we propose a new method called MoRA, which employs a square matrix to achieve high-rank updating while maintaining the same number of trainable parameters. To achieve it, we introduce the corresponding non-parameter operators to reduce the input dimension and increase the output dimension for the square matrix. Furthermore, these operators ensure that the weight can be merged back into LLMs, which makes our method can be deployed like LoRA. We perform a comprehensive evaluation of our method across five tasks: instruction tuning, mathematical reasoning, continual pretraining, memory and pretraining. Our method outperforms LoRA on memory-intensive tasks and achieves comparable performance on other tasks.

cs.CL↗

arXiv2024

Improving Domain Adaptation through Extended-Text Reading Comprehension

To enhance the domain-specific capabilities of large language models, continued pre-training on a domain-specific corpus is a prevalent method. Recent work demonstrates that adapting models using reading comprehension data formatted by regex-based patterns can significantly improve performance on domain-specific tasks. However, regex-based patterns are incapable of parsing raw corpora using domain-specific knowledge. Furthermore, the question and answer pairs are extracted directly from the corpus in predefined formats offers limited context. To address this limitation, we improve reading comprehension via LLM and clustering. LLM focuses on leveraging domain knowledge within the corpus to refine comprehension stage, while clustering supplies relevant knowledge by extending the context to enrich reading stage. Additionally, our method incorporates parameter-efficient fine-tuning to improve the efficiency of domain adaptation. In comparison to AdaptLLM, our method achieves an improvement exceeding 5% in domain-specific tasks. Our code will available at https://github.com/microsoft/LMOps.

cs.CL↗

arXiv2023

Combating Multi-path Interference to Improve Chirp-based Underwater Acoustic Communication

Linear chirp-based underwater acoustic communication has been widely used due to its reliability and long-range transmission capability. However, unlike the counterpart chirp technology in wireless -- LoRa, its throughput is severely limited by the number of modulated chirps in a symbol. The fundamental challenge lies in the underwater multi-path channel, where the delayed copied of one symbol may cause inter-symbol and intra-symbol interfere. In this paper, we present UWLoRa+, a system that realizes the same chirp modulation as LoRa with higher data rate, and enhances LoRa's design to address the multi-path challenge via the following designs: a) we replace the linear chirp used by LoRa with the non-linear chirp to reduce the signal interference range and the collision probability; b) we design an algorithm that first demodulates each path and then combines the demodulation results of detected paths; and c) we replace the Hamming codes used by LoRa with the non-binary LDPC codes to mitigate the impact of the inevitable collision.Experiment results show that the new designs improve the bit error rate (BER) by 3x, and the packet error rate (PER) significantly, compared with the LoRa's naive design. Compared with an state-of-the-art system for decoding underwater LoRa chirp signal, UWLoRa+ improves the throughput by up to 50 times.

eess.SP↗

arXiv2023

Event-based Dynamic Graph Representation Learning for Patent Application Trend Prediction

Accurate prediction of what types of patents that companies will apply for in the next period of time can figure out their development strategies and help them discover potential partners or competitors in advance. Although important, this problem has been rarely studied in previous research due to the challenges in modelling companies' continuously evolving preferences and capturing the semantic correlations of classification codes. To fill in this gap, we propose an event-based dynamic graph learning framework for patent application trend prediction. In particular, our method is founded on the memorable representations of both companies and patent classification codes. When a new patent is observed, the representations of the related companies and classification codes are updated according to the historical memories and the currently encoded messages. Moreover, a hierarchical message passing mechanism is provided to capture the semantic proximities of patent classification codes by updating their representations along the hierarchical taxonomy. Finally, the patent application trend is predicted by aggregating the representations of the target company and classification codes from static, dynamic, and hierarchical perspectives. Experiments on real-world data demonstrate the effectiveness of our approach under various experimental conditions, and also reveal the abilities of our method in learning semantics of classification codes and tracking technology developing trajectories of companies.

cs.AI↗

arXiv2023

Knowledge-based Multiple Adaptive Spaces Fusion for Recommendation

Since Knowledge Graphs (KGs) contain rich semantic information, recently there has been an influx of KG-enhanced recommendation methods. Most of existing methods are entirely designed based on euclidean space without considering curvature. However, recent studies have revealed that a tremendous graph-structured data exhibits highly non-euclidean properties. Motivated by these observations, in this work, we propose a knowledge-based multiple adaptive spaces fusion method for recommendation, namely MCKG. Unlike existing methods that solely adopt a specific manifold, we introduce the unified space that is compatible with hyperbolic, euclidean and spherical spaces. Furthermore, we fuse the multiple unified spaces in an attention manner to obtain the high-quality embeddings for better knowledge propagation. In addition, we propose a geometry-aware optimization strategy which enables the pull and push processes benefited from both hyperbolic and spherical spaces. Specifically, in hyperbolic space, we set smaller margins in the area near to the origin, which is conducive to distinguishing between highly similar positive items and negative ones. At the same time, we set larger margins in the area far from the origin to ensure the model has sufficient error tolerance. The similar manner also applies to spherical spaces. Extensive experiments on three real-world datasets demonstrate that the MCKG has a significant improvement over state-of-the-art recommendation methods. Further ablation experiments verify the importance of multi-space fusion and geometry-aware optimization strategy, justifying the rationality and effectiveness of MCKG.

cs.IR↗

arXiv2023

Seq-HGNN: Learning Sequential Node Representation on Heterogeneous Graph

Recent years have witnessed the rapid development of heterogeneous graph neural networks (HGNNs) in information retrieval (IR) applications. Many existing HGNNs design a variety of tailor-made graph convolutions to capture structural and semantic information in heterogeneous graphs. However, existing HGNNs usually represent each node as a single vector in the multi-layer graph convolution calculation, which makes the high-level graph convolution layer fail to distinguish information from different relations and different orders, resulting in the information loss in the message passing. %insufficient mining of information. To this end, we propose a novel heterogeneous graph neural network with sequential node representation, namely Seq-HGNN. To avoid the information loss caused by the single vector node representation, we first design a sequential node representation learning mechanism to represent each node as a sequence of meta-path representations during the node message passing. Then we propose a heterogeneous representation fusion module, empowering Seq-HGNN to identify important meta-paths and aggregate their representations into a compact one. We conduct extensive experiments on four widely used datasets from Heterogeneous Graph Benchmark (HGB) and Open Graph Benchmark (OGB). Experimental results show that our proposed method outperforms state-of-the-art baselines in both accuracy and efficiency. The source code is available at https://github.com/nobrowning/SEQ_HGNN.

cs.LG↗

arXiv2023

Scaling Sentence Embeddings with Large Language Models

Large language models (LLMs) have recently garnered significant interest. With in-context learning, LLMs achieve impressive results in various natural language tasks. However, the application of LLMs to sentence embeddings remains an area of ongoing research. In this work, we propose an in-context learning-based method aimed at improving sentence embeddings performance. Our approach involves adapting the previous prompt-based representation method for autoregressive models, constructing a demonstration set that enables LLMs to perform in-context learning, and scaling up the LLMs to different model sizes. Through extensive experiments, in-context learning enables LLMs to generate high-quality sentence embeddings without any fine-tuning. It helps LLMs achieve performance comparable to current contrastive learning methods. By scaling model size, we find scaling to more than tens of billion parameters harms the performance on semantic textual similarity (STS) tasks. However, the largest model outperforms other counterparts and achieves the new state-of-the-art result on transfer tasks. We also fine-tune LLMs with current contrastive learning approach, and the 2.7B OPT model, incorporating our prompt-based method, surpasses the performance of 4.8B ST5, achieving the new state-of-the-art results on STS tasks. Our code is available at https://github.com/kongds/scaling_sentemb.

cs.CL↗

arXiv2023

Modeling Dynamic Heterogeneous Graph and Node Importance for Future Citation Prediction

Accurate citation count prediction of newly published papers could help editors and readers rapidly figure out the influential papers in the future. Though many approaches are proposed to predict a paper's future citation, most ignore the dynamic heterogeneous graph structure or node importance in academic networks. To cope with this problem, we propose a Dynamic heterogeneous Graph and Node Importance network (DGNI) learning framework, which fully leverages the dynamic heterogeneous graph and node importance information to predict future citation trends of newly published papers. First, a dynamic heterogeneous network embedding module is provided to capture the dynamic evolutionary trends of the whole academic network. Then, a node importance embedding module is proposed to capture the global consistency relationship to figure out each paper's node importance. Finally, the dynamic evolutionary trend embeddings and node importance embeddings calculated above are combined to jointly predict the future citation counts of each paper, by a log-normal distribution model according to multi-faced paper node representations. Extensive experiments on two large-scale datasets demonstrate that our model significantly improves all indicators compared to the SOTA models.

cs.DL↗

arXiv2023

Pruning Pre-trained Language Models Without Fine-Tuning

To overcome the overparameterized problem in Pre-trained Language Models (PLMs), pruning is widely used as a simple and straightforward compression method by directly removing unimportant weights. Previous first-order methods successfully compress PLMs to extremely high sparsity with little performance drop. These methods, such as movement pruning, use first-order information to prune PLMs while fine-tuning the remaining weights. In this work, we argue fine-tuning is redundant for first-order pruning, since first-order pruning is sufficient to converge PLMs to downstream tasks without fine-tuning. Under this motivation, we propose Static Model Pruning (SMP), which only uses first-order pruning to adapt PLMs to downstream tasks while achieving the target sparsity level. In addition, we also design a new masking function and training objective to further improve SMP. Extensive experiments at various sparsity levels show SMP has significant improvements over first-order and zero-order methods. Unlike previous first-order methods, SMP is also applicable to low sparsity and outperforms zero-order methods. Meanwhile, SMP is more parameter efficient than other methods due to it does not require fine-tuning.

cs.CL↗

arXiv2022

RHCO: A Relation-aware Heterogeneous Graph Neural Network with Contrastive Learning for Large-scale Graphs

Heterogeneous graph neural networks (HGNNs) have been widely applied in heterogeneous information network tasks, while most HGNNs suffer from poor scalability or weak representation when they are applied to large-scale heterogeneous graphs. To address these problems, we propose a novel Relation-aware Heterogeneous Graph Neural Network with Contrastive Learning (RHCO) for large-scale heterogeneous graph representation learning. Unlike traditional heterogeneous graph neural networks, we adopt the contrastive learning mechanism to deal with the complex heterogeneity of large-scale heterogeneous graphs. We first learn relation-aware node embeddings under the network schema view. Then we propose a novel positive sample selection strategy to choose meaningful positive samples. After learning node embeddings under the positive sample graph view, we perform a cross-view contrastive learning to obtain the final node representations. Moreover, we adopt the label smoothing technique to boost the performance of RHCO. Extensive experiments on three large-scale academic heterogeneous graph datasets show that RHCO achieves best performance over the state-of-the-art models.

cs.LG↗

arXiv2022

Exploring the Confounding Factors of Academic Career Success: An Empirical Study with Deep Predictive Modeling

Understanding determinants of success in academic careers is critically important to both scholars and their employing organizations. While considerable research efforts have been made in this direction, there is still a lack of a quantitative approach to modeling the academic careers of scholars due to the massive confounding factors. To this end, in this paper, we propose to explore the determinants of academic career success through an empirical and predictive modeling perspective, with a focus on two typical academic honors, i.e., IEEE Fellow and ACM Fellow. We analyze the importance of different factors quantitatively, and obtain some insightful findings. Specifically, we analyze the co-author network and find that potential scholars work closely with influential scholars early on and more closely as they grow. Then we compare the academic performance of male and female Fellows. After comparison, we find that to be elected, females need to put in more effort than males. In addition, we also find that being a Fellow could not bring the improvements of citations and productivity growth. We hope these derived factors and findings can help scholars to improve their competitiveness and develop well in their academic careers.

cs.CY↗

arXiv2022

Exploiting Global and Local Hierarchies for Hierarchical Text Classification

Hierarchical text classification aims to leverage label hierarchy in multi-label text classification. Existing methods encode label hierarchy in a global view, where label hierarchy is treated as the static hierarchical structure containing all labels. Since global hierarchy is static and irrelevant to text samples, it makes these methods hard to exploit hierarchical information. Contrary to global hierarchy, local hierarchy as a structured labels hierarchy corresponding to each text sample. It is dynamic and relevant to text samples, which is ignored in previous methods. To exploit global and local hierarchies,we propose Hierarchy-guided BERT with Global and Local hierarchies (HBGL), which utilizes the large-scale parameters and prior language knowledge of BERT to model both global and local hierarchies.Moreover,HBGL avoids the intentional fusion of semantic and hierarchical modules by directly modeling semantic and hierarchical information with BERT.Compared with the state-of-the-art method HGCLR,our method achieves significant improvement on three benchmark datasets.

cs.CL↗

arXiv2022

PromptBERT: Improving BERT Sentence Embeddings with Prompts

We propose PromptBERT, a novel contrastive learning method for learning better sentence representation. We firstly analyze the drawback of current sentence embedding from original BERT and find that it is mainly due to the static token embedding bias and ineffective BERT layers. Then we propose the first prompt-based sentence embeddings method and discuss two prompt representing methods and three prompt searching methods to make BERT achieve better sentence embeddings. Moreover, we propose a novel unsupervised training objective by the technology of template denoising, which substantially shortens the performance gap between the supervised and unsupervised settings. Extensive experiments show the effectiveness of our method. Compared to SimCSE, PromptBert achieves 2.29 and 2.58 points of improvement based on BERT and RoBERTa in the unsupervised setting.

cs.CL↗

arXiv2022

Contrastive Learning with Bidirectional Transformers for Sequential Recommendation

Contrastive learning with Transformer-based sequence encoder has gained predominance for sequential recommendation. It maximizes the agreements between paired sequence augmentations that share similar semantics. However, existing contrastive learning approaches in sequential recommendation mainly center upon left-to-right unidirectional Transformers as base encoders, which are suboptimal for sequential recommendation because user behaviors may not be a rigid left-to-right sequence. To tackle that, we propose a novel framework named \textbf{C}ontrastive learning with \textbf{Bi}directional \textbf{T}ransformers for sequential recommendation (\textbf{CBiT}). Specifically, we first apply the slide window technique for long user sequences in bidirectional Transformers, which allows for a more fine-grained division of user sequences. Then we combine the cloze task mask and the dropout mask to generate high-quality positive samples and perform multi-pair contrastive learning, which demonstrates better performance and adaptability compared with the normal one-pair contrastive learning. Moreover, we introduce a novel dynamic loss reweighting strategy to balance between the cloze task loss and the contrastive loss. Experiment results on three public benchmark datasets show that our model outperforms state-of-the-art models for sequential recommendation.

cs.IR↗

arXiv2022

Learnable Model Augmentation Self-Supervised Learning for Sequential Recommendation

Sequential Recommendation aims to predict the next item based on user behaviour. Recently, Self-Supervised Learning (SSL) has been proposed to improve recommendation performance. However, most of existing SSL methods use a uniform data augmentation scheme, which loses the sequence correlation of an original sequence. To this end, in this paper, we propose a Learnable Model Augmentation self-supervised learning for sequential Recommendation (LMA4Rec). Specifically, LMA4Rec first takes model augmentation as a supplementary method for data augmentation to generate views. Then, LMA4Rec uses learnable Bernoulli dropout to implement model augmentation learnable operations. Next, self-supervised learning is used between the contrastive views to extract self-supervised signals from an original sequence. Finally, experiments on three public datasets show that the LMA4Rec method effectively improves sequential recommendation performance compared with baseline methods.

cs.IR↗

arXiv2022

Aligning Domain-specific Distribution and Classifier for Cross-domain Classification from Multiple Sources

While Unsupervised Domain Adaptation (UDA) algorithms, i.e., there are only labeled data from source domains, have been actively studied in recent years, most algorithms and theoretical results focus on Single-source Unsupervised Domain Adaptation (SUDA). However, in the practical scenario, labeled data can be typically collected from multiple diverse sources, and they might be different not only from the target domain but also from each other. Thus, domain adapters from multiple sources should not be modeled in the same way. Recent deep learning based Multi-source Unsupervised Domain Adaptation (MUDA) algorithms focus on extracting common domain-invariant representations for all domains by aligning distribution of all pairs of source and target domains in a common feature space. However, it is often very hard to extract the same domain-invariant representations for all domains in MUDA. In addition, these methods match distributions without considering domain-specific decision boundaries between classes. To solve these problems, we propose a new framework with two alignment stages for MUDA which not only respectively aligns the distributions of each pair of source and target domains in multiple specific feature spaces, but also aligns the outputs of classifiers by utilizing the domain-specific decision boundaries. Extensive experiments demonstrate that our method can achieve remarkable results on popular benchmark datasets for image classification.

cs.LG↗

arXiv2021

Improving Non-autoregressive Generation with Mixup Training

While pre-trained language models have achieved great success on various natural language understanding tasks, how to effectively leverage them into non-autoregressive generation tasks remains a challenge. To solve this problem, we present a non-autoregressive generation model based on pre-trained transformer models. To bridge the gap between autoregressive and non-autoregressive models, we propose a simple and effective iterative training method called MIx Source and pseudo Target (MIST). Unlike other iterative decoding methods, which sacrifice the inference speed to achieve better performance based on multiple decoding iterations, MIST works in the training stage and has no effect on inference time. Our experiments on three generation benchmarks including question generation, summarization and paraphrase generation, show that the proposed framework achieves the new state-of-the-art results for fully non-autoregressive models. We also demonstrate that our method can be used to a variety of pre-trained models. For instance, MIST based on the small pre-trained model also obtains comparable performance with seq2seq models.

cs.CL↗