论文检索

Dou Hu, Lingwei Wei, Wei Zhou, Songlin Hu

This paper proposes a new principled multi-task representation learning framework (InfoMTL) to extract noise-invariant sufficient representations for all tasks. It ensures sufficiency of shared representations for all tasks and mitigates the negative effect of redundant features, which can enhance language understanding of pre-trained language models (PLMs) under the multi-task paradigm. Firstly, a shared information maximization principle is proposed to learn more sufficient shared representations for all target tasks. It can avoid the insufficiency issue arising from representation compression in the multi-task paradigm. Secondly, a task-specific information minimization principle is designed to mitigate the negative effect of potential redundant features in the input for each task. It can compress task-irrelevant redundant information and preserve necessary information relevant to the target for multi-task prediction. Experiments on six classification benchmarks show that our method outperforms 12 comparative multi-task methods under the same multi-task settings, especially in data-constrained and noisy scenarios. Extensive experiments demonstrate that the learned representations are more sufficient, data-efficient, and robust.

Bo Hu, Kai Zhang, Yanghai Zhang, Yuyang Ye

In recent years, deep multimodal learning has seen significant advancements. However, there remains a lack of multimodal fusion methods capable of dynamically adjusting the weighting of information both within and across modalities based on input samples. In the domain of multimodal intent recognition, the text modality often contains the most relevant information for intent detection, while the audio and visual modalities provide comparatively less critical information. There is a significant variation in the density of important information across different modalities and samples. To address this challenge, we propose a Dynamic Attention Allocation Fusion (DAF) method with an adaptive network structure that dynamically allocates attention both within individual modalities and across multiple modalities. This approach enables the model to focus more effectively on the most informative modalities and their respective internal features. Furthermore, we introduce a multi-view contrastive learning framework based on DAF (MVCL-DAF). This framework uses distinct and isolated modules to process information from various modalities, taking inspiration from the way the human brain processes multimodal information. Each modality independently infers intent using its respective module, while DAF integrates the multimodal information to produce a comprehensive global intent prediction. The text modality, functioning as the primary modality due to its rich semantic content, guides the other modules in the multi-view contrastive learning process. Extensive experiments demonstrate that our approach significantly outperforms existing state-of-the-art methods.

Yue Hou, He Zhu, Ruomei Liu, Yingke Su, Jinxiang Xia, Junran Wu, Ke Xu

With the emerging of huge amount of unlabeled data, unsupervised out-of-distribution (OOD) detection is vital for ensuring the reliability of graph neural networks (GNNs) by identifying OOD samples from in-distribution (ID) ones during testing, where encountering novel or unknown data is inevitable. Existing methods often suffer from compromised performance due to redundant information in graph structures, which impairs their ability to effectively differentiate between ID and OOD data. To address this challenge, we propose SEGO, an unsupervised framework that integrates structural entropy into OOD detection regarding graph classification. Specifically, within the architecture of contrastive learning, SEGO introduces an anchor view in the form of coding tree by minimizing structural entropy. The obtained coding tree effectively removes redundant information from graphs while preserving essential structural information, enabling the capture of distinct graph patterns between ID and OOD samples. Furthermore, we present a multi-grained contrastive learning scheme at local, global, and tree levels using triplet views, where coding trees with essential information serve as the anchor view. Extensive experiments on real-world datasets validate the effectiveness of SEGO, demonstrating superior performance over state-of-the-art baselines in OOD detection. Specifically, our method achieves the best performance on 9 out of 10 dataset pairs, with an average improvement of 3.7% on OOD detection datasets, significantly surpassing the best competitor by 10.8% on the FreeSolv/ToxCast dataset pair.

Ryien Hosseini, Filippo Simini, Venkatram Vishwanath, Henry Hoffmann

Recent advancements in graph representation learning have shifted attention towards dynamic graphs, which exhibit evolving topologies and features over time. The increased use of such graphs creates a paramount need for generative models suitable for applications such as data augmentation, obfuscation, and anomaly detection. However, there are few generative techniques that handle continuously changing temporal graph data; existing work largely relies on augmenting static graphs with additional temporal information to model dynamic interactions between nodes. In this work, we propose a fundamentally different approach: We instead directly model interactions as a joint probability of an edge forming between two nodes at a given time. This allows us to autoregressively generate new synthetic dynamic graphs in a largely assumption free, scalable, and inductive manner. We formalize this approach as DG-Gen, a generative framework for continuous time dynamic graphs, and demonstrate its effectiveness over five datasets. Our experiments demonstrate that DG-Gen not only generates higher fidelity graphs compared to traditional methods but also significantly advances link prediction tasks.

Di Hong, Yueming Wang

Spiking Neural Networks (SNNs) are promising for low-power computation due to their event-driven mechanism but often suffer from lower accuracy compared to Artificial Neural Networks (ANNs). ANN-to-SNN knowledge distillation can improve SNN performance, but previous methods either focus solely on label information, missing valuable intermediate layer features, or use a layer-wise approach that neglects spatial and temporal semantic inconsistencies, leading to performance degradation. To address these limitations, we propose a novel method called self-attentive spatio-temporal calibration (SASTC). SASTC uses self-attention to identify semantically aligned layer pairs between ANN and SNN, both spatially and temporally. This enables the autonomous transfer of relevant semantic information. Extensive experiments show that SASTC outperforms existing methods, effectively solving the mismatching problem. Superior accuracy results include 95.12% on CIFAR-10, 79.40% on CIFAR-100 with 2 time steps, and 68.69% on ImageNet with 4 time steps for static datasets, and 97.92% on DVS-Gesture and 83.60% on DVS-CIFAR10 for neuromorphic datasets. This marks the first time SNNs have outperformed ANNs on both CIFAR-10 and CIFAR-100, shedding the new light on the potential applications of SNNs.

Cheng-Yao Hong, Tyng-Luh Liu

Token compression techniques, such as token merging and pruning, are essential for alleviating the substantial computational burden caused by the proliferation of tokens within attention mechanisms. However, current methods often rely on token-to-token distances or similarity metrics to evaluate token importance, which is inadequate in the context of modern promptable designs and frameworks that are gaining prominence. To address this limitation, we introduce a novel and effective merging strategy called “Multimodal Promptable Token Merging” (MPTM). The proposed method leverages a multimodal, prompt-centric methodology, assessing the proximity between tokens of each input modality and the multimodal prompt to efficiently eliminate redundant tokens while preserving those rich in information. Extensive experiments demonstrate that MPTM significantly reduces computational costs without compromising essential information in generative image tasks. When integrated into diffusion-based detection architectures, MPTM outperforms existing state-of-the-art methods by 2.3% in object detection tasks. Additionally, when applied to multimodal diffusion models, MPTM maintains high-quality output while achieving a 2.9-fold increase in throughput, highlighting its versatility.

Tilman Hoffbauer, Holger H. Hoos, Jakob Bossek

Time series forecasting requires reliable uncertainty estimates. Gaussian process regression provides a powerful framework for modelling this in a probabilistic fashion. However, its application to large time series is challenging, due to its cubic time complexity and quadratic memory requirement. In this work, we present KernelMatmul, a novel method that accelerates Gaussian process inference and thus facilitates scaling of Gaussian process regression to large, irregularly sampled and multi-output time series. Leveraging conjugate gradients in combination with sparsity approximation, KernelMatmul achieves time and memory complexity linear in the number of samples. We thoroughly benchmark our new method against multiple baselines to demonstrate its benefits and limitations, both in efficiency and accuracy.

Niklas Hoepner, Ilaria Tiddi, Herke Van Hoof

The scalability of instructable agents in robotics or gaming is often hindered by limited data that pairs instructions with agent trajectories. However, large datasets of unannotated trajectories containing sequences of various agent behaviour (play trajectories) are often available. In a semi-supervised setup, we explore methods to extract labelled segments from play trajectories. The goal is to augment a small annotated dataset of instruction-trajectory pairs to improve the performance of an instruction-following policy trained downstream via imitation learning. Assuming little variation in segment length, recent video segmentation methods can effectively extract labelled segments. To address the constraint of segment length, we propose Play Segmentation (PS), a probabilistic model that finds maximum likely segmentations of extended subsegments, while only being trained on individual instruction segments. Our results in a game environment and a simulated robotic gripper setting underscore the importance of segmentation; randomly sampled segments diminish performance, while incorporating labelled segments from PS improves policy performance to the level of a policy trained on twice the amount of labelled data.

Van Thuy Hoang, O-Joun Lee

This study aims to build a pre-trained Graph Neural Network (GNN) model on molecules without human annotations or prior knowledge. Although various attempts have been proposed to overcome limitations in acquiring labeled molecules, the previous pre-training methods still rely on semantic subgraphs, i.e., functional groups. Only focusing on the functional groups could overlook the graph-level distinctions. The key challenge to build a pre-trained GNN on molecules is how to (1) generate well-distinguished graph-level representations and (2) automatically discover the functional groups without prior knowledge. To solve it, we propose a novel Subgraph-conditioned Graph Information Bottleneck, named S-CGIB, for pre-training GNNs to recognize core subgraphs (graph cores) and significant subgraphs. The main idea is that the graph cores contain compressed and sufficient information that could generate well-distinguished graph-level representations and reconstruct the input graph conditioned on significant subgraphs across molecules under the S-CGIB principle. To discover significant subgraphs without prior knowledge about functional groups, we propose generating a set of functional group candidates, i.e., ego networks, and using an attention-based interaction between the graph core and the candidates. Despite being identified from self-supervised learning, our learned subgraphs match the real-world functional groups. Extensive experiments on molecule datasets across various domains demonstrate the superiority of S-CGIB.

Yuya Hikima, Akiko Takeda

In this study, we consider an optimization problem with uncertainty dependent on decision variables, which has recently attracted attention due to its importance in machine learning and pricing applications. In this problem, the gradient of the objective function cannot be obtained explicitly because the decision-dependent distribution is unknown. Therefore, several zeroth-order methods have been proposed, which obtain noisy objective values by sampling and update the iterates. Although these existing methods have theoretical convergence for optimization problems with decision-dependent uncertainty, they require strong assumptions about the function and distribution or exhibit large variances in their gradient estimators. To overcome these issues, we propose two zeroth-order methods under mild assumptions. First, we develop a zeroth-order method with a new one-point gradient estimator including a variance reduction parameter. The proposed method updates the decision variables while adjusting the variance reduction parameter. Second, we develop a zeroth-order method with a two-point gradient estimator. There are situations where only one-point estimators can be used, but if both one-point and two-point estimators are available, it is more practical to use the two-point estimator. As theoretical results, we show the convergence of our methods to stationary points and provide the worst-case iteration and sample complexity analysis. Our simulation experiments with real data on a retail service application show that our methods output solutions with lower objective values than the conventional zeroth-order methods.

Nong Minh Hieu, Antoine Ledent, Yunwen Lei, Cheng Yeaw Ku

In this paper, we present generalization bounds for the unsupervised risk in the Deep Contrastive Representation Learning framework, which employs deep neural networks as representation functions. We approach this problem from two angles. On the one hand, we derive a parameter-counting bound that scales with the overall size of the neural networks. On the other hand, we provide a norm-based bound that scales with the norms of neural networks' weight matrices. Ignoring logarithmic factors, the bounds are independent of the size of the tuples provided for contrastive learning. To the best of our knowledge, this property is only shared by one other work, which employed a different proof strategy and suffers from very strong exponential dependence on the depth of the network which is due to a use of the peeling technique. Our results circumvent this by leveraging powerful results on covering numbers with respect to uniform norms over samples. In addition, we utilize loss augmentation techniques to further reduce the dependency on matrix norms and the implicit dependence on network depth. In fact, our techniques allow us to produce many bounds for the contrastive learning setting with similar architectural dependencies as in the study of the sample complexity of ordinary loss functions, thereby bridging the gap between the learning theories of contrastive learning and DNNs.

Asela Hevapathige, Qing Wang, Ahad N. Zehmakan

Influence maximization is a key topic in data mining, with broad applications in social network analysis and viral marketing. In recent years, researchers have increasingly turned to machine learning techniques to address this problem. By learning the underlying diffusion processes from data, these methods improve the generalizability of solutions while optimizing objectives to identify the optimal seed set for maximizing influence. Nonetheless, two fundamental challenges remain unresolved: (1) While Graph Neural Networks (GNNs) are increasingly employed to learn diffusion models, their traditional architectures often fail to capture the complex dynamics of influence diffusion, (2) Designing optimization objectives is inherently difficult due to the combinatorial explosion associated with solving this problem. To address these challenges, we propose a novel framework, DeepSN. Our framework employs sheaf neural diffusion to learn diverse influence patterns in a data-driven, end-to-end manner, providing enhanced separability in capturing diffusion characteristics. We also propose an optimization technique that accounts for overlapping influence between vertices, significantly reducing the search space and facilitating the identification of the optimal seed set efficiently. Finally, we conduct extensive experiments on both synthetic and real-world datasets to demonstrate the effectiveness of our framework.

Marzi Heidari, Yuhong Guo

Semi-supervised learning (SSL) is a fundamental task in machine learning, empowering models to extract valuable insights from datasets with limited labeled samples and a large amount of unlabeled data. Although pseudo-labeling is a widely used approach for SSL that generates pseudo-labels for unlabeled data and leverages them as ground truth labels for training, traditional pseudo-labeling techniques often face challenges that significantly decrease the quality of pseudo-labels and hence the overall model performance. In this paper, we propose a novel Bi-level Optimization method for Pseudo-label Learning (BOPL) to boost semi-supervised training. It treats pseudo-labels as latent variables, and optimizes the model parameters and pseudo-labels jointly within a bi-level optimization framework. By enabling direct optimization over the pseudo-labels towards maximizing the prediction model performance, the method is expected to produce high-quality pseudo-labels. To evaluate the effectiveness of the proposed approach, we conduct extensive experiments on multiple SSL benchmarks. The experimental results show the proposed BOPL outperforms the state-of-the-art SSL techniques.

Zhouyu He, Peng Qiao, Rongchun Li, Yong Dou, Yusong Tan

As the demands for superior agents grow, the training complexity of Deep Reinforcement Learning (DRL) becomes higher. Thus, accelerating training of DRL has become a major research focus. Dividing the DRL training process into sub-tasks and using parallel computation can effectively reduce training costs. However, current DRL training systems lack sufficient parallelization due to data assignment between sub-task components. This assignment issue has been ignored, but addressing it can further boost training efficiency. Therefore, we propose a high-throughput distributed RL training system called TianJi. It relaxes assignment dependencies between sub-task components and enables event-driven asynchronous communication. Meanwhile, TianJi maintains clear boundaries between sub-task components. To address convergence uncertainty from relaxed assignment dependencies, TianJi proposes a distributed strategy based on the balance of sample production and consumption. The strategy controls the staleness of samples to correct their quality, ensuring convergence. We conducted extensive experiments. TianJi achieves a convergence time acceleration ratio of up to 4.37 compared to related comparison frameworks. When scaled to eight computational nodes, TianJi shows a convergence time speedup of 1.6 and a throughput speedup of 7.13 relative to XingTian, emonstrating its capability to accelerate training and scalability. In data transmission efficiency experiments, TianJi significantly outperforms other frameworks, approaching hardware limits. TianJi also shows effectiveness in on-policy algorithms, achieving convergence time acceleration ratios of 4.36 and 2.95 compared to RLlib and XingTian.

Xinyu He, Xinhui Li, Xiaojie Guo

Domain adaptive object detection (DAOD) aims to generalize an object detector trained on labeled source-domain data to a target domain without annotations, the core principle of which is source-target feature alignment. Typically, existing approaches employ adversarial learning to align the distributions of the source and target domains as a whole, barely considering the varying significance of distinct regions, say instances under different circumstances and foreground vs background areas, during feature alignment. To overcome the shortcoming, we investigate a differential feature alignment strategy. Specifically, a prediction-discrepancy feedback instance alignment module (dubbed PDFA) is designed to adaptively assign higher weights to instances of higher teacher-student detection discrepancy, effectively handling heavier domain-specific information. Additionally, an uncertainty-based foreground-oriented image alignment module (UFOA) is proposed to explicitly guide the model to focus more on regions of interest. Extensive experiments on widely-used DAOD datasets together with ablation studies are conducted to demonstrate the efficacy of our proposed method and reveal its superiority over other SOTA alternatives.

Xing He, Jiahao Chen, Yuwen Pu, Qingming Li, Chunyi Zhou, Yingcai Wu, Jinbao Li, Shouling Ji

In the burgeoning domain of machine learning, the reliance on third-party services for model training and the adoption of pre-trained models have surged. However, this reliance introduces vulnerabilities to model hijacking attacks, where adversaries manipulate models to perform unintended tasks, leading to significant security and ethical concerns, like turning an ordinary image classifier into a tool for detecting faces in pornographic content, all without the model owner’s knowledge. This paper introduces Category-Agnostic Model Hijacking (CAMH), a novel model hijacking attack method capable of addressing the challenges of class number mismatch, data distribution divergence, and performance balance between the original and hijacking tasks. CAMH incorporates synchronized training layers, random noise optimization, and a dual-loop optimization approach to ensure minimal impact on the original task’s performance while effectively executing the hijacking task. We evaluate CAMH across multiple benchmark datasets and network architectures, demonstrating its potent attack effectiveness while ensuring minimal degradation in the performance of the original task.

Weinan He, Zilei Wang, Yixin Zhang

Universal Domain Adaptation (UniDA) focuses on transferring source domain knowledge to the target domain under both domain shift and unknown category shift. Its main challenge lies in identifying common class samples and aligning them. Current methods typically obtain target domain semantics centers from an unconstrained continuous image representation space. Due to domain shift and the unknown number of clusters, these centers often result in complex and less robust alignment algorithm. In this paper, based on vision-language models, we search for semantic centers in a semantically meaningful and discrete text representation space. The constrained space ensures almost no domain bias and appropriate semantic granularity for these centers, enabling a simple and robust adaptation algorithm. Specifically, we propose TArget Semantics Clustering (TASC) via Text Representations, which leverages information maximization as a unified objective and involves two stages. First, with the frozen encoders, a greedy search-based framework is used to search for an optimal set of text embeddings to represent target semantics. Second, with the search results fixed, encoders are refined based on gradient descent, simultaneously achieving robust domain alignment and private class clustering. Additionally, we propose Universal Maximum Similarity (UniMS), a scoring function tailored for detecting open-set samples in UniDA. Experimentally, we evaluate the universality of UniDA algorithms under four category shift scenarios. Extensive experiments on four benchmarks demonstrate the effectiveness and robustness of our method, which has achieved state-of-the-art performance.

Wanggui He, Siming Fu, Mushui Liu, Xierui Wang, Wenyi Xiao, Fangxun Shu, Yi Wang, Lei Zhang, Zhelun Yu, Haoyuan Li 等

Auto-regressive models have made significant progress in the realm of text-to-image synthesis, yet devising an appropriate model architecture and training strategy to achieve a satisfactory level remains an important avenue of exploration. In this work, we introduce MARS, a novel framework for T2I generation that incorporates a specially designed Semantic Vision-Language Integration Expert (SemVIE). This innovative component integrates pre-trained LLMs by independently processing linguistic and visual information—freezing the textual component while fine-tuning the visual component. This methodology preserves the NLP capabilities of LLMs while imbuing them with exceptional visual understanding. Building upon the powerful base of the pre-trained Qwen-7B, MARS stands out with its bilingual generative capabilities corresponding to both English and Chinese language prompts and the capacity for joint image and text generation. The flexibility of this framework lends itself to migration towards any-to-any task adaptability. Furthermore, MARS employs a multi-stage training strategy that first establishes robust image-text alignment through complementary bidirectional tasks and subsequently concentrates on refining the T2I generation process, significantly augmenting text-image synchrony and the granularity of image details. Notably, MARS requires only 9% of the GPU days needed by SD1.5, yet it achieves remarkable results across a variety of benchmarks, illustrating the training efficiency and the potential for swift deployment in various applications.

Qiuyan He, Minghua Deng

Universal domain adaptation (UniDA) transfers knowledge from a labelled source domain to an unlabelled target domain under domain-shift and category-shift for annotation. In reality, due to privacy protection or other limits, not only source data but also pre-trained models on it may be unavailable when training on target data. In this paper, we go a step further to explore the black-box universal domain adaptation (B^2-UniDA) problem. It requires tackling the labelling task under shifts by only accessing the interface of pre-trained source models. To this end, we introduce GSS which proposes a novel sample selection criterion based on gradient descent and Bayes' Theorem to identify samples of potential unknown classes. This criterion doesn't require manually-set thresholds depending on data used and is suitable for various datasets. GSS builds an open-set classifier and enables it to estimate probabilities of belonging to each class including the unknown category and adjust estimates adaptively. To overcome class-imbalance, especially imbalance between the unknown and known classes, we propose a balancing mechanism by measuring training status and estimating DA type. In addition to distilling knowledge from source model outputs, we focus on mining the categorical structure of target domain by self-training. Experiments on benchmarks show the state-of-the-art performance of GSS compared to typical methods, including source models or source data dependent methods.

Qian He, Wenqi Liang, Chunhui Hao, Gan Sun, Jiandong Tian

Mimicking the real interaction trajectory in the inference of the world model has been shown to improve the sample efficiency of model-based reinforcement learning (MBRL) algorithms. Many methods directly use known state sequences for reasoning. However, this approach fails to enhance the quality of reasoning by capturing the subtle variation between states. Much like how humans infer trends in event development from this variation, in this work, we introduce Global-Local variation Awareness Mamba-based world model (GLAM) that improves reasoning quality by perceiving and predicting variation between states. GLAM comprises two Mamba-based parallel reasoning modules, GMamba and LMamba, which focus on perceiving variation from global and local perspectives, respectively, during the reasoning process. GMamba focuses on identifying patterns of variation between states in the input sequence and leverages these patterns to enhance the prediction of future state variation. LMamba emphasizes reasoning about unknown information, such as rewards, termination signals, and visual representations, by perceiving variation in adjacent states. By integrating the strengths of the two modules, GLAM accounts for higher-value variation in environmental changes, providing the agent with more efficient imagination-based training. We demonstrate that our method outperforms existing methods in normalized human scores on the Atari 100k benchmark.