IJCAI 2024 Papers

Social learning plays an important role in the development of human intelligence. As children, we imitate our parent's speech patterns until we are able to produce sounds; we learn from them praising us and scolding us, and as adults, we learn by working with others. In this work, we survey the degree to which this developmental paradigm -- social learning -- has been mirrored in machine learning. In particular, since learning socially requires interacting with others, we are interested in how embodied agents can and have utilised these techniques. This is especially in light of the degree to which recent advances in natural language processing (NLP) enable us to perform new forms of social learning. We look at how behaviour cloning and next-token prediction mirror human imitation, how learning from human feedback mirrors human education, and how we can go further to enable fully communicative agents that learn from each other. We find that while individual social learning techniques have been used successfully, there has been little unifying work showing how to bring them together into socially embodied agents.

New rideshare and shared mobility services have transformed urban mobility in recent years. Such services have the potential to improve efficiency and reduce costs by allowing users to share rides in high-capacity vehicles and vans. Most transit agencies already operate various ridepooling services, including microtransit and paratransit. However, the objectives and constraints for implementing these services vary greatly between agencies and can be challenging. First, off-the-shelf ridepooling formulations must be adapted for real-world conditions and constraints. Second, the lack of modular and reusable software makes it hard to implement and evaluate new ridepooling algorithms and approaches in real-world settings. We demonstrate a modular on-demand public transportation scheduling software for microtransit and paratransit services. The software is aimed at transit agencies looking to incorporate state-of-the-art rideshare and ridepooling algorithms in their everyday operations. We provide management software for dispatchers and mobile applications for drivers and users and conclude with results from the demonstration in Chattanooga, TN.

Recent studies have raised questions about the suitability of the Transformer architecture for long sequence time-series forecasting. These forecasting models leverage Transformers to capture dependencies between multiple time steps in a time series, with embedding tokens composed of data from individual time steps. However, challenges arise when applying Transformers to predict long sequences with strong periodicity, leading to performance degradation and increased computational burden. Furthermore, embedding tokens formed one time step at a time may struggle to reveal meaningful information in long sequences, failing to capture correlations between different time steps. In this study, we propose Skip-Timeformer, a Transformer-based model that utilizes a skip-time interaction for long sequence time-series forecasting. Specifically, we decompose the time series into multiple subsequences based on different time intervals, embedding various time steps into variable tokens across multiple sequences. The skip-time interaction mechanism utilizes these variable tokens to capture dependencies in the skip-time dimension. Additionally, skip-time interaction is employed to learn dependencies between sequences missed by multiple skip time steps. The Skip-Timeformer model demonstrates state-of-the-art performance on various real-world datasets, further enhancing the long sequence forecasting capabilities of the Transformer variations and better adapting to arbitrary lookback windows.

Recent sketch synthesis methods have demonstrated the capability of generating lifelike outcomes. However, these methods directly encode the entire sketches making it challenging to decouple the strokes from the sketches and have difficulty in controlling local sketch synthesis, e.g., stroke editing. Besides, the sketch editing task encounters the issue of accurately positioning the edited strokes, because users may not be able to draw on the exact position and the same stroke may appear in various locations in different sketches. We propose SketchEdit to realize flexible editing of sketches at the stroke-level for the first time. To tackle the challenge of decoupling strokes, SketchEdit divides a drawing sequence of a sketch into a series of strokes based on the pen state, aligns the stroke segments to have the same starting position, and learns the embeddings of every stroke by a proposed stroke encoder. Moreover, we overcome the problem of stroke placement via a diffusion process, which progressively generates the locations for the strokes to be synthesized, using the stroke features as the guiding condition. Experiments demonstrate that SketchEdit is effective for stroke-level sketch editing and sketch reconstruction. The source code is publicly available at https://github.com/CMACH508/SketchEdit/.

Previous deep multi-view clustering methods usually design un-shared encoders to explore the cluster information among multi-view data, but they are difficult to customize the encoders for individual views and easily increase information loss. To address these issues, we propose a simple yet effective contrastive multi-view clustering framework. Specifically, different from using feature-level fusion in previous methods, we first propose a data-level fusion method to fuse multi-view information, which produces a fused data to replace all views and thus avoids customizing networks for different views. Then, we simulate the data noise and unavailability in multiple views to design two kinds of data augmentation for the fused data, making a shared encoder with simple contrastive learning to learn robust features and achieve the interaction across views. As a result, our method is a general framework and we base on it to conduct feature clustering and end-to-end clustering. Extensive experiments demonstrate that our method can explore the discriminative information in multi-view data and achieve superior clustering performance.

In real-world scenarios, human actions often fall into a long-tailed distribution. It makes the existing skeleton-based action recognition works, which are mostly designed based on balanced datasets, suffer from a sharp performance degradation. Recently, many efforts have been made to image/video long-tailed learning. However, directly applying them to skeleton data can be sub-optimal due to the lack of consideration of the crucial spatial-temporal motion patterns, especially for some modality-specific methodologies such as data augmentation. To this end, considering the crucial role of the body parts in the spatially concentrated human actions, we attend to the mixing augmentations and propose a novel method, Shap-Mix, which improves long-tailed learning by mining representative motion patterns for tail categories. Specifically, we first develop an effective spatial-temporal mixing strategy for the skeleton to boost representation quality. Then, the employed saliency guidance method is presented, consisting of the saliency estimation based on Shapley value and a tail-aware mixing policy. It preserves the salient motion parts of minority classes in mixed data, explicitly establishing the relationships between crucial body structure cues and high-level semantics. Extensive experiments on three large-scale skeleton datasets show our remarkable performance improvement under both long-tailed and balanced settings. Our project is publicly available at: https://jhang2020.github.io/Projects/Shap-Mix/Shap-Mix.html.

Recommender systems have been successfully applied in many applications. Nonetheless, recent studies demonstrate that recommender systems are vulnerable to membership inference attacks (MIAs), leading to the leakage of users’ membership privacy. However, existing MIAs relying on shadow training suffer a large performance drop when the attacker lacks knowledge of the training data distribution and the model architecture of the target recommender system. To better understand the privacy risks of recommender systems, we propose shadow-free MIAs that directly leverage a user’s recommendations for membership inference. Without shadow training, the proposed attack can conduct MIAs efficiently and effectively under a practice scenario where the attacker is given only black-box access to the target recommender system. The proposed attack leverages an intuition that the recommender system personalizes a user’s recommendations if his historical interactions are used by it. Thus, an attacker can infer membership privacy by determining whether the recommendations are more similar to the interactions or the general popular items. We conduct extensive experiments on benchmark datasets across various recommender systems. Remarkably, our attack achieves far better attack accuracy with low false positive rates than baselines while with a much lower computational cost.

The integration of visual cues has revitalized the performance of the target speech extraction task, elevating it to the forefront of the field. Nevertheless, this multi-modal learning paradigm often encounters the challenge of modality imbalance. In audio-visual target speech extraction tasks, the audio modality tends to dominate, potentially overshadowing the importance of visual guidance. To tackle this issue, we propose AVSepChain, drawing inspiration from the speech chain concept. Our approach partitions the audio-visual target speech extraction task into two stages: speech perception and speech production. In the speech perception stage, audio serves as the dominant modality, while visual information acts as the conditional modality. Conversely, in the speech production stage, the roles are reversed. This transformation of modality status aims to alleviate the problem of modality imbalance. Additionally, we introduce a contrastive semantic matching loss to ensure that the semantic information conveyed by the generated speech aligns with the semantic information conveyed by lip movements during the speech production stage. Through extensive experiments conducted on multiple benchmark datasets for audio-visual target speech extraction, we showcase the superior performance achieved by our proposed method.

Knowledge distillation, transferring knowledge from a teacher model to a student model, has emerged as a powerful technique in neural machine translation for compressing models or simplifying training targets. Knowledge distillation encompasses two primary methods: sentence-level distillation and token-level distillation. In sentence-level distillation, the student model is trained to align with the output of the teacher model, which can alleviate the training difficulty and give student model a comprehensive understanding of global structure. Differently, token-level distillation requires the student model to learn the output distribution of the teacher model, facilitating a more fine-grained transfer of knowledge. Studies have revealed divergent performances between sentence-level and token-level distillation across different scenarios, leading to the confusion on the empirical selection of knowledge distillation methods. In this study, we argue that token-level distillation, with its more complex objective (i.e., distribution), is better suited for “simple” scenarios, while sentence-level distillation excels in “complex” scenarios. To substantiate our hypothesis, we systematically analyze the performance of distillation methods by varying the model size of student models, the complexity of text, and the difficulty of decoding procedure. While our experimental results validate our hypothesis, defining the complexity level of a given scenario remains a challenging task. So we further introduce a novel hybrid method that combines token-level and sentence-level distillation through a gating mechanism, aiming to leverage the advantages of both individual methods. Experiments demonstrate that the hybrid method surpasses the performance of token-level or sentence-level distillation methods and the previous works by a margin, demonstrating the effectiveness of the proposed hybrid method.

Modern industrial facilities generate large volumes of raw sensor data during the production process. This data is used to monitor and control the processes and can be analyzed to detect and predict process abnormalities. Typically, the data has to be annotated by experts in order to be used in predictive modeling. However, manual annotation of large amounts of data can be difficult in industrial settings. In this paper, we propose SensorSCAN, a novel method for unsupervised fault detection and diagnosis, designed for industrial chemical process monitoring. We demonstrate our model's performance on two publicly available datasets of the Tennessee Eastman Process with various faults. The results show that our method significantly outperforms existing approaches (+0.2-0.3 TPR for a fixed FPR) and effectively detects most of the process faults without expert annotation. Moreover, we show that the model fine-tuned on a small fraction of labeled data nearly reaches the performance of a SOTA model trained on the full dataset. We also demonstrate that our method is suitable for real-world applications where the number of faults is not known in advance. The code is available at https://github.com/AIRI-Institute/sensorscan

Assumption-based argumentation (ABA) is an argumentative formalism that allows for reasoning on the basis of defeasible assumptions and strict rules. Standard semantics for this formalism sometimes give rise to problematic behaviour in the presence of rules with assumptions in their heads. In this paper, we introduce a six-valued labelling semantics that overcomes these shortcomings while preserving all the usual properties of the standard Dung-style three-valued semantics for ABA frameworks, including existence of the complete semantics, uniqueness of the grounded semantics and preservation of the computational complexity of all main reasoning processes.

Contrastive learning based on data augmentation techniques has recently achieved substantial advancement in learning a representation well-suited for anomaly detection in image domain. However, due to the lack of spatial structure, designing effective data augmentation methods for tabular data remains challenging. Conventional techniques, such as random mask, disregard the inter-feature correlations and fail to accurately represent the data. To address this issue, we propose a novel augmentation technique called SemanticMask which leverages the semantic information from column names to generate better augmented views. SemanticMask aims to ensure that the shared information between views contains sufficient information for anomaly detection without redundancy. We analyze the relationship between shared information and anomaly detection performance and empirically demonstrate that good views for tabular anomaly detection tasks are feature-dependent. Our experiment results validate the superiority of SemanticMask over the state-of-the-art anomaly detection methods and existing augmentation techniques for tabular data. In further evaluations of the multi-class novelty detection task, SemanticMask also significantly outperforms the baseline.

Multi-view clustering (MVC) is a long-standing topic in machine learning and data mining community, focusing on investigating and utilizing the relationships among views for final consistent data cluster structure discovery. Generally, weighted MVC is one of the popular methods working by learning and applying the view weight/importance on each view for fully exploring the complementary information across views. However, most existing weighted MVCs only consider the quality of each view, ignoring the vital role of pseudo label self-supervision information in weight learning. In this work, we propose a novel self-supervised weighted information bottleneck (SWIB) method for solving the multi-view clustering problem. It combines the weighted information from different views based on information bottleneck theory, and the view weight learning mechanism is newly designed by simultaneously taking into accounting both the quality of view-contained information and the self-supervised information on the data partition of each view. Experimental results on multi-view text, multi-feature image, multi-angle video, and multi-modal text-image dataset as well as large-scale datasets show the superiority of the SWIB method. To our knowledge, this is the first work incorporating the self-supervised learning into weighted multi-view clustering.

Policy-Space Response Oracles (PSRO) as a general algorithmic framework has achieved state-of-the-art performance in learning equilibrium policies of two-player zero-sum games. However, the hand-crafted hyperparameter value selection in most of the existing works requires extensive domain knowledge, forming the main barrier to applying PSRO to different games. In this work, we make the first attempt to investigate the possibility of self-adaptively determining the optimal hyperparameter values in the PSRO framework. Our contributions are three-fold: (1) Using several hyperparameters, we propose a parametric PSRO that unifies the gradient descent ascent (GDA) and different PSRO variants. (2) We propose the self-adaptive PSRO (SPSRO) by casting the hyperparameter value selection of the parametric PSRO as a hyperparameter optimization (HPO) problem where our objective is to learn an HPO policy that can self-adaptively determine the optimal hyperparameter values during the running of the parametric PSRO. (3) To overcome the poor performance of online HPO methods, we propose a novel offline HPO approach to optimize the HPO policy based on the Transformer architecture. Experiments on various two-player zero-sum games demonstrate the superiority of SPSRO over different baselines.

Forecasting time series in imbalanced data presents a significant research challenge that requires considerable attention. Although there are specialized techniques available to tackle imbalanced time series prediction, existing approaches tend to prioritize extreme predictions at the expense of compromising the forecasting accuracy of normal samples. We in this paper propose an extreme penalized loss function that relaxes the constraint on overestimating extreme events, thereby imposing great penalties on both normal and underestimating extreme events. In addition, we provide a self-adaptive way for setting the hyperparameters of the loss function. Then, both the proposed loss function and an attention module are integrated with LSTM networks in a decomposition-based framework. Extensive experiments conducted on real-world datasets demonstrate the superiority of our framework compared to other state-of-the-art approaches for both time series prediction and block maxima prediction tasks.

Climate change is one of the most critical challenges that our planet is facing today. Rising global temperatures are already affecting Earth's weather and climate patterns with an increased frequency of unpredictable and extreme events. Future projections for climate change research are based on computer models like Earth System Models (ESMs). Climate simulations typically run on a coarser grid due to the high computational resources required, and then undergo a lighter downscaling process to obtain data on a finer grid. This work presents a self-supervised deep learning model that does not require high resolution ground truth data for downscaling. This is realized by leveraging salient distribution patterns and the hidden dependencies between weather variables for an individual data point at runtime. We propose three climate-specific components that well represent the patterns of underlying weather variables and learn intricate inter-variable dependencies. Extensive evaluation with 2x, 3x, and 4x scaling factors demonstrates that our model obtains 8% to 47% performance gain over existing baselines while greatly reducing the overall runtime. The improved performance and no dependence on high resolution ground truth data make our method a valuable tool for future climate research.

In text recognition, self-supervised pre-training emerges as a good solution to reduce dependence on expansive annotated real data. Previous studies primarily focus on local visual representation by leveraging mask image modeling or sequence contrastive learning. However, they omit modeling the linguistic information in text images, which is crucial for recognizing text. To simultaneously capture local character features and linguistic information in visual space, we propose Symmetric Superimposition Modeling (SSM). The objective of SSM is to reconstruct the direction-specific pixel and feature signals from the symmetrically superimposed input. Specifically, we add the original image with its inverted views to create the symmetrically superimposed inputs. At the pixel level, we reconstruct the original and inverted images to capture character shapes and texture-level linguistic context. At the feature level, we reconstruct the feature of the same original image and inverted image with different augmentations to model the semantic-level linguistic context and the local character discrimination. In our design, we disrupt the character shape and linguistic rules. Consequently, the dual-level reconstruction facilitates understanding character shapes and linguistic information from the perspective of visual texture and feature semantics. Experiments on various text recognition benchmarks demonstrate the effectiveness and generality of SSM, with 4.1\% average performance gains and 86.6% new state-of-the-art average word accuracy on Union14M benchmarks. The code is available at https://github.com/FaltingsA/SSM.

Nighttime self-supervised monocular depth estimation has received increasing attention in recent years. However, using night images for self-supervision is unreliable because the photometric consistency assumption is usually violated in the videos taken under complex lighting conditions. Even with domain adaptation or photometric loss repair, performance is still limited by the poor supervision of night images on trainable networks. In this paper, we propose a self-supervised nighttime monocular depth estimation method that does not use any night images during training. Our framework utilizes day images as a stable source for self-supervision and applies physical priors (e.g., wave optics, reflection model and read-shot noise model) to compensate for some key day-night differences. With day-to-night data distribution compensation, our framework can be trained in an efficient one-stage self-supervised manner. Though no nighttime images are considered during training, qualitative and quantitative results demonstrate that our method achieves SoTA depth estimating results on the challenging nuScenes-Night and RobotCar-Night compared with existing methods.

Free-hand sketch, as a versatile medium of communication, can be viewed as a collection of strokes arranged in a spatial layout to convey a concept. Due to the abstract nature of the sketches, changes in stroke position may make them difficult to recognize. Recently, Graphic sketch representations are effective in representing sketches. However, existing methods overlook the significance of the spatial layout of strokes and the phenomenon of strokes being drawn in the wrong positions is common. Therefore, we developed a self-supervised task to correct stroke placement and investigate the impact of spatial layout on learning sketch representations. For this task, we propose a spatially aware method, named SketchGloc, utilizing multiple graphs for graphic sketch representations. This method utilizes grids for each stroke to describe the spatial layout with other strokes, allowing for the construction of multiple graphs. Unlike other methods that rely on a single graph, this design conveys more detailed spatial layout information and alleviates the impact of misplaced strokes. The experimental results demonstrate that our model outperforms existing methods in both our proposed task and the traditional controllable sketch synthesis task. Additionally, we found that SketchGloc can learn more robust representations under our proposed task setting. The source code is available at https://github.com/CMACH508/SketchGloc.