Parameter-efficient fine-tuning (PEFT) has emerged as an effective method for adapting pre-trained language models to various tasks efficiently. Recently, there has been a growing interest in transferring knowledge from one or multiple tasks to the downstream target task to achieve performance improvements. However, current approaches typically either train adapters on individual tasks or distill shared knowledge from source tasks, failing to fully exploit task-specific knowledge and the correlation between source and target tasks. To overcome these limitations, we propose PEMT, a novel parameter-efficient fine-tuning framework based on multi-task transfer learning. PEMT extends the mixture-of-experts (MoE) framework to capture the transferable knowledge as a weighted combination of adapters trained on source tasks. These weights are determined by a gated unit, measuring the correlation between the target and each source task using task description prompt vectors. To fully exploit the task-specific knowledge, we also propose the Task Sparsity Loss to improve the sparsity of the gated unit. We conduct experiments on a broad range of tasks over 17 datasets. The experimental results demonstrate our PEMT yields stable improvements over full fine-tuning, and state-of-the-art PEFT and knowledge transferring methods on various tasks. The results highlight the effectiveness of our method which is capable of sufficiently exploiting the knowledge and correlation features across multiple tasks.
The integration of Large Language Models (LLMs) with Graph Representation Learning (GRL) marks a significant evolution in analyzing complex data structures. This collaboration harnesses the sophisticated linguistic capabilities of LLMs to improve the contextual understanding and adaptability of graph models, thereby broadening the scope and potential of GRL. Despite a growing body of research dedicated to integrating LLMs into the graph domain, a comprehensive review that deeply analyzes the core components and operations within these models is notably lacking. Our survey fills this gap by proposing a novel taxonomy that breaks down these models into primary components and operation techniques from a novel technical perspective. We further dissect recent literature into two primary components including knowledge extractors and organizers, and two operation techniques including integration and training stratigies, shedding light on effective model design and training strategies. Additionally, we identify and explore potential future research avenues in this nascent yet underexplored field, proposing paths for continued progress.
While existing code large language models (code LLMs) exhibit impressive capabilities in code generation, their autoregressive sequential generation inherently lacks reversibility. This limitation hinders them from timely correcting previous missing statements during coding as humans do, often leading to error propagation and suboptimal performance. We introduce JumpCoder, a novel modelagnostic framework that enables online modification and non-sequential generation to augment the code LLMs. The key idea behind JumpCoder is to insert new code into the currently generated code when necessary during generation, which is achieved through an auxiliary infilling model that works in tandem with the code LLM. Since identifying the best infill position beforehand is intractable, we adopt an infill-first, judge-later strategy, which experiments with filling at the $k$ most critical positions following the generation of each line, and uses an Abstract Syntax Tree (AST) parser alongside the Generation Model Scoring to effectively judge the validity of each potential infill. Extensive experiments using six state-of-the-art code LLMs across multiple benchmarks consistently indicate significant improvements over all baselines. Notably, JumpCoder assists code LLMs in achieving up to a 3.6% increase in Pass@1 for Python, 6.3% for Java, and 3.7% for C++ in the multilingual HumanEval benchmarks. Our code is public at https://github.com/Keytoyze/JumpCoder.
Recent research has demonstrated the efficacy of pre-training graph neural networks (GNNs) to capture the transferable graph semantics and enhance the performance of various downstream tasks. However, the semantic knowledge learned from pretext tasks might be unrelated to the downstream task, leading to a semantic gap that limits the application of graph pre-training. To reduce this gap, traditional approaches propose hybrid pre-training to combine various pretext tasks together in a multi-task learning fashion and learn multi-grained knowledge, which, however, cannot distinguish tasks and results in some transferable task-specific knowledge distortion by each other. Moreover, most GNNs cannot distinguish nodes located in different parts of the graph, making them fail to learn position-specific knowledge and lead to suboptimal performance. In this work, inspired by the prompt-based tuning in natural language processing, we propose a unified framework for graph hybrid pre-training which injects the task identification and position identification into GNNs through a prompt mechanism, namely multi-task graph dual prompt (ULTRA-DP). Based on this framework, we propose a prompt-based transferability test to find the most relevant pretext task in order to reduce the semantic gap. To implement the hybrid pre-training tasks, beyond the classical edge prediction task (node-node level), we further propose a novel pre-training paradigm based on a group of $k$-nearest neighbors (node-group level). The combination of them across different scales is able to comprehensively express more structural semantics and derive richer multi-grained knowledge. Extensive experiments show that our proposed ULTRA-DP can significantly enhance the performance of hybrid pre-training methods and show the generalizability to other pre-training tasks and backbone architectures.
Recent years have witnessed the success of introducing Transformers to time series forecasting. From a data generation perspective, we illustrate that existing Transformers are susceptible to distribution shifts driven by temporal contexts, whether observed or unobserved. Such context-driven distribution shift (CDS) introduces biases in predictions within specific contexts and poses challenges for conventional training paradigm. In this paper, we introduce a universal calibration methodology for the detection and adaptation of CDS with a trained Transformer model. To this end, we propose a novel CDS detector, termed the "residual-based CDS detector" or "Reconditionor", which quantifies the model's vulnerability to CDS by evaluating the mutual information between prediction residuals and their corresponding contexts. A high Reconditionor score indicates a severe susceptibility, thereby necessitating model adaptation. In this circumstance, we put forth a straightforward yet potent adapter framework for model calibration, termed the "sample-level contextualized adapter" or "SOLID". This framework involves the curation of a contextually similar dataset to the provided test sample and the subsequent fine-tuning of the model's prediction layer with a limited number of steps. Our theoretical analysis demonstrates that this adaptation strategy is able to achieve an optimal equilibrium between bias and variance. Notably, our proposed Reconditionor and SOLID are model-agnostic and readily adaptable to a wide range of Transformers. Extensive experiments show that SOLID consistently enhances the performance of current SOTA Transformers on real-world datasets, especially on cases with substantial CDS detected by the proposed Reconditionor, thus validate the effectiveness of the calibration approach.
The application of Unbiased Learning to Rank (ULTR) is widespread in modern systems for training unbiased ranking models from biased click logs. The key is to explicitly model a generation process for user behavior and fit click data based on examination hypothesis. Previous research found empirically that the true latent relevance can be recovered in most cases as long as the clicks are perfectly fitted. However, we demonstrate that this is not always achievable, resulting in a significant reduction in ranking performance. In this work, we aim to answer if or when the true relevance can be recovered from click data, which is a foundation issue for ULTR field. We first define a ranking model as identifiable if it can recover the true relevance up to a scaling transformation, which is enough for pairwise ranking objective. Then we explore an equivalent condition for identifiability that can be novely expressed as a graph connectivity test problem: if and only if a graph (namely identifiability graph, or IG) constructed on the underlying structure of the dataset is connected, we can guarantee that the relevance can be correctly recovered. When the IG is not connected, there may be bad cases leading to poor ranking performance. To address this issue, we propose two methods, namely node intervention and node merging, to modify the dataset and restore connectivity of the IG. Empirical results obtained on a simulation dataset and two LTR benchmark datasets confirm the validity of our proposed theorems and show the effectiveness of our methods in mitigating data bias when the relevance model is unidentifiable.
Recent studies have highlighted the limitations of message-passing based graph neural networks (GNNs), e.g., limited model expressiveness, over-smoothing, over-squashing, etc. To alleviate these issues, Graph Transformers (GTs) have been proposed which work in the paradigm that allows message passing to a larger coverage even across the whole graph. Hinging on the global range attention mechanism, GTs have shown a superpower for representation learning on homogeneous graphs. However, the investigation of GTs on heterogeneous information networks (HINs) is still under-exploited. In particular, on account of the existence of heterogeneity, HINs show distinct data characteristics and thus require different treatment. To bridge this gap, in this paper we investigate the representation learning on HINs with Graph Transformer, and propose a novel model named HINormer, which capitalizes on a larger-range aggregation mechanism for node representation learning. In particular, assisted by two major modules, i.e., a local structure encoder and a heterogeneous relation encoder, HINormer can capture both the structural and heterogeneous information of nodes on HINs for comprehensive node representations. We conduct extensive experiments on four HIN benchmark datasets, which demonstrate that our proposed model can outperform the state-of-the-art.
Unbiased learning to rank (ULTR) aims to train an unbiased ranking model from biased user click logs. Most of the current ULTR methods are based on the examination hypothesis (EH), which assumes that the click probability can be factorized into two scalar functions, one related to ranking features and the other related to bias factors. Unfortunately, the interactions among features, bias factors and clicks are complicated in practice, and usually cannot be factorized in this independent way. Fitting click data with EH could lead to model misspecification and bring the approximation error. In this paper, we propose a vector-based EH and formulate the click probability as a dot product of two vector functions. This solution is complete due to its universality in fitting arbitrary click functions. Based on it, we propose a novel model named Vectorization to adaptively learn the relevance embeddings and sort documents by projecting embeddings onto a base vector. Extensive experiments show that our method significantly outperforms the state-of-the-art ULTR methods on complex real clicks as well as simple simulated clicks.
Sequential user behavior modeling plays a crucial role in online user-oriented services, such as product purchasing, news feed consumption, and online advertising. The performance of sequential modeling heavily depends on the scale and quality of historical behaviors. However, the number of user behaviors inherently follows a long-tailed distribution, which has been seldom explored. In this work, we argue that focusing on tail users could bring more benefits and address the long tails issue by learning transferrable parameters from both optimization and feature perspectives. Specifically, we propose a gradient alignment optimizer and adopt an adversarial training scheme to facilitate knowledge transfer from the head to the tail. Such methods can also deal with the cold-start problem of new users. Moreover, it could be directly adaptive to various well-established sequential models. Extensive experiments on four real-world datasets verify the superiority of our framework compared with the state-of-the-art baselines.