Jun Wang

Zihan Liao, Jun Wang, Hang Yu et al.

Processing long contexts is increasingly important for Large Language Models (LLMs) in tasks like multi-turn dialogues, code generation, and document summarization. This paper addresses the challenges of achieving high long-context performance, low computational complexity, and compatibility with pretrained models -- collectively termed the ``impossible triangle''. We introduce E2LLM (Encoder Elongated Large Language Models), a novel approach that effectively navigates this paradox. E2LLM divides long contexts into chunks, compresses each into soft prompts using a pretrained text encoder, and aligns these representations with a decoder-only LLM via an adapter. To enhance the LLM's reasoning with these soft prompts, we employ two training objectives: encoder output reconstruction and long-context instruction fine-tuning. Extensive experiments reveal that E2LLM not only outperforms 8 state-of-the-art (SOTA) methods in effectiveness and efficiency for document summarization and question answering, but also achieves the best performance on LongBench v2 among models of comparable size.

Xuxiang Jiang, Yinhao Xiao, Jun Wang et al.

Vulnerability identification is crucial for cyber security in the software-related industry. Early identification methods require significant manual efforts in crafting features or annotating vulnerable code. Although the recent pre-trained models alleviate this issue, they overlook the multiple rich structural information contained in the code itself. In this paper, we propose a novel Multi-View Pre-Trained Model (MV-PTM) that encodes both sequential and multi-type structural information of the source code and uses contrastive learning to enhance code representations. The experiments conducted on two public datasets demonstrate the superiority of MV-PTM. In particular, MV-PTM improves GraphCodeBERT by 3.36\% on average in terms of F1 score.

Renrong Shao, Wei Zhang, Kangyang Luo et al.

Source-free domain adaptation (SFDA) aims to address the challenge of adapting to a target domain without accessing the source domain directly. However, due to the inaccessibility of source domain data, deterministic invariable features cannot be obtained. Current mainstream methods primarily focus on evaluating invariant features in the target domain that closely resemble those in the source domain, subsequently aligning the target domain with the source domain. However, these methods are susceptible to hard samples and influenced by domain bias. In this paper, we propose a Consistent Assistant Domains Transformer for SFDA, abbreviated as CADTrans, which solves the issue by constructing invariable feature representations of domain consistency. Concretely, we develop an assistant domain module for CADTrans to obtain diversified representations from the intermediate aggregated global attentions, which addresses the limitation of existing methods in adequately representing diversity. Based on assistant and target domains, invariable feature representations are obtained by multiple consistent strategies, which can be used to distinguish easy and hard samples. Finally, to align the hard samples to the corresponding easy samples, we construct a conditional multi-kernel max mean discrepancy (CMK-MMD) strategy to distinguish between samples of the same category and those of different categories. Extensive experiments are conducted on various benchmarks such as Office-31, Office-Home, VISDA-C, and DomainNet-126, proving the significant performance improvements achieved by our proposed approaches. Code is available at https://github.com/RoryShao/CADTrans.git.

Renrong Shao, Wei Zhang, Jun Wang

Source-free domain adaptation (SFDA) involves training a model on source domain and then applying it to a related target domain without access to the source data and labels during adaptation. The complexity of scene information and lack of the source domain make SFDA a difficult task. Recent studies have shown promising results, but many approaches to domain adaptation concentrate on domain shift and neglect the effects of negative transfer, which may impede enhancements of model performance during adaptation. n this paper, addressing this issue, we propose a novel framework of Attention Residual Fusion Network (ARFNet) based on contrast learning for SFDA to alleviate negative transfer and domain shift during the progress of adaptation, in which attention residual fusion, global-local attention contrast, and dynamic centroid evaluation are exploited. Concretely, the attention mechanism is first exploited to capture the discriminative region of the target object. Then, in each block, attention features are decomposed into spatial-wise and channel-wise attentions to achieve the cross-layer attention residual fusion progressively and self-distillation. During adaptation progress, we contrast global and local representations to improve the perceptual capabilities of different categories, which enables the model to discriminate variations between inner-class and intra-class. Finally, a dynamic centroid evaluation strategy is exploited to evaluate the trustworthy centroids and labels for self-supervised self-distillation, which aims to accurately approximate the center of the source domain and pseudo-labels to mitigate domain shift. To validate the efficacy, we execute comprehensive experiments on five benchmarks of varying scales. Experimental outcomes indicate that our method surpasses other techniques, attaining superior performance across SFDA benchmarks.

Weinan Zhang, Lingxi Chen, Jun Wang

User behaviour targeting is essential in online advertising. Compared with sponsored search keyword targeting and contextual advertising page content targeting, user behaviour targeting builds users' interest profiles via tracking their online behaviour and then delivers the relevant ads according to each user's interest, which leads to higher targeting accuracy and thus more improved advertising performance. The current user profiling methods include building keywords and topic tags or mapping users onto a hierarchical taxonomy. However, to our knowledge, there is no previous work that explicitly investigates the user online visits similarity and incorporates such similarity into their ad response prediction. In this work, we propose a general framework which learns the user profiles based on their online browsing behaviour, and transfers the learned knowledge onto prediction of their ad response. Technically, we propose a transfer learning model based on the probabilistic latent factor graphic models, where the users' ad response profiles are generated from their online browsing profiles. The large-scale experiments based on real-world data demonstrate significant improvement of our solution over some strong baselines.

Weinan Zhang, Tianming Du, Jun Wang

Predicting user responses, such as click-through rate and conversion rate, are critical in many web applications including web search, personalised recommendation, and online advertising. Different from continuous raw features that we usually found in the image and audio domains, the input features in web space are always of multi-field and are mostly discrete and categorical while their dependencies are little known. Major user response prediction models have to either limit themselves to linear models or require manually building up high-order combination features. The former loses the ability of exploring feature interactions, while the latter results in a heavy computation in the large feature space. To tackle the issue, we propose two novel models using deep neural networks (DNNs) to automatically learn effective patterns from categorical feature interactions and make predictions of users' ad clicks. To get our DNNs efficiently work, we propose to leverage three feature transformation methods, i.e., factorisation machines (FMs), restricted Boltzmann machines (RBMs) and denoising auto-encoders (DAEs). This paper presents the structure of our models and their efficient training algorithms. The large-scale experiments with real-world data demonstrate that our methods work better than major state-of-the-art models.