IJCAI 2022 论文列表

Graph neural networks have been widely used for a variety of learning tasks. Link prediction is a relatively under-studied graph learning task, with current state-of-the-art models based on one- or two-layer shallow graph auto-encoder (GAE) architectures. In this paper, we overcome the limitation of current methods for link prediction of non-Euclidean network data, which can only use shallow GAEs and variational GAEs. Our proposed methods innovatively incorporate standard auto-encoders (AEs) into the architectures of GAEs to capitalize on the intimate coupling of node and edge information in complex network data. Empirically, extensive experiments on various datasets demonstrate the competitive performance of our proposed approach. Theoretically, we prove that our deep extensions can inclusively express multiple polynomial filters with different orders. The codes of this paper are available at https://github.com/xinxingwu-uk/DGAE.

Graph Convolutional Networks (GCNs) achieve an impressive performance due to the remarkable representation ability in learning the graph information. However, GCNs, when implemented on a deep network, require expensive computation power, making them difficult to be deployed on battery-powered devices. In contrast, Spiking Neural Networks (SNNs), which perform a bio-fidelity inference process, offer an energy-efficient neural architecture. In this work, we propose SpikingGCN, an end-to-end framework that aims to integrate the embedding of GCNs with the biofidelity characteristics of SNNs. The original graph data are encoded into spike trains based on the incorporation of graph convolution. We further model biological information processing by utilizing a fully connected layer combined with neuron nodes. In a wide range of scenarios (e.g., citation networks, image graph classification, and recommender systems), our experimental results show that the proposed method could gain competitive performance against state-of-the-art approaches. Furthermore, we show that SpikingGCN on a neuromorphic chip can bring a clear advantage of energy efficiency into graph data analysis, which demonstrates its great potential to construct environment-friendly machine learning models.

The emotion recognition in conversation (ERC) task aims to predict the emotion label of an utterance in a conversation. Since the dependencies between speakers are complex and dynamic, which consist of intra- and inter-speaker dependencies, the modeling of speaker-specific information is a vital role in ERC. Although existing researchers have proposed various methods of speaker interaction modeling, they cannot explore dynamic intra- and inter-speaker dependencies jointly, leading to the insufficient comprehension of context and further hindering emotion prediction. To this end, we design a novel speaker modeling scheme that explores intra- and inter-speaker dependencies jointly in a dynamic manner. Besides, we propose a Speaker-Guided Encoder-Decoder (SGED) framework for ERC, which fully exploits speaker information for the decoding of emotion. We use different existing methods as the conversational context encoder of our framework, showing the high scalability and flexibility of the proposed framework. Experimental results demonstrate the superiority and effectiveness of SGED.

Dense captioning in 3D point clouds is an emerging vision-and-language task involving object-level 3D scene understanding. Apart from coarse semantic class prediction and bounding box regression as in traditional 3D object detection, 3D dense captioning aims at producing a further and finer instance-level label of natural language description on visual appearance and spatial relations for each scene object of interest. To detect and describe objects in a scene, following the spirit of neural machine translation, we propose a transformer-based encoder-decoder architecture, namely SpaCap3D, to transform objects into descriptions, where we especially investigate the relative spatiality of objects in 3D scenes and design a spatiality-guided encoder via a token-to-token spatial relation learning objective and an object-centric decoder for precise and spatiality-enhanced object caption generation. Evaluated on two benchmark datasets, ScanRefer and ReferIt3D, our proposed SpaCap3D outperforms the baseline method Scan2Cap by 4.94% and 9.61% in CIDEr@0.5IoU, respectively. Our project page with source code and supplementary files is available at https://SpaCap3D.github.io/.

Transformers have been successfully applied to the visual tracking task and significantly promote tracking performance. The self-attention mechanism designed to model long-range dependencies is the key to the success of Transformers. However, self-attention lacks focusing on the most relevant information in the search regions, making it easy to be distracted by background. In this paper, we relieve this issue with a sparse attention mechanism by focusing the most relevant information in the search regions, which enables a much accurate tracking. Furthermore, we introduce a double-head predictor to boost the accuracy of foreground-background classification and regression of target bounding boxes, which further improve the tracking performance. Extensive experiments show that, without bells and whistles, our method significantly outperforms the state-of-the-art approaches on LaSOT, GOT-10k, TrackingNet, and UAV123, while running at 40 FPS. Notably, the training time of our method is reduced by 75% compared to that of TransT. The source code and models are available at https://github.com/fzh0917/SparseTT.

Standard convolution operations can effectively perform feature extraction and representation but result in high computational cost, largely due to the generation of the original convolution kernel corresponding to the channel dimension of the feature map, which will cause unnecessary redundancy. In this paper, we focus on kernel generation and present an interpretable span strategy, named SpanConv, for the effective construction of kernel space. Specifically, we first learn two navigated kernels with single channel as bases, then extend the two kernels by learnable coefficients, and finally span the two sets of kernels by their linear combination to construct the so-called SpanKernel. The proposed SpanConv is realized by replacing plain convolution kernel by SpanKernel. To verify the effectiveness of SpanConv, we design a simple network with SpanConv. Experiments demonstrate the proposed network significantly reduces parameters comparing with benchmark networks for remote sensing pansharpening, while achieving competitive performance and excellent generalization. Code is available at https://github.com/zhi-xuan-chen/IJCAI-2022 SpanConv.

For the pansharpening problem, previous convolutional neural networks (CNNs) mainly concatenate high-resolution panchromatic (PAN) images and low-resolution multispectral (LR-MS) images in their architectures, which ignores the distinctive attributes of different sources. In this paper, we propose a convolution network with source-adaptive discriminative kernels, called ADKNet, for the pansharpening task. Those kernels consist of spatial kernels generated from PAN images containing rich spatial details and spectral kernels generated from LR-MS images containing abundant spectral information. The kernel generating process is specially designed to extract information discriminately and effectively. Furthermore, the kernels are learned in a pixel-by-pixel manner to characterize different information in distinct areas. Extensive experimental results indicate that ADKNet outperforms current state-of-the-art (SOTA) pansharpening methods in both quantitative and qualitative assessments, in the meanwhile only with about 60,000 network parameters. Also, the proposed network is extended to the hyperspectral image super-resolution (HSISR) problem, still yields SOTA performance, proving the universality of our model. The code is available at http://github.com/liangjiandeng/ADKNet.

Synthesizer is a type of electronic musical instrument that is now widely used in modern music production and sound design. Each parameters configuration of a synthesizer produces a unique timbre and can be viewed as a unique instrument. The problem of estimating a set of parameters configuration that best restore a sound timbre is an important yet complicated problem, i.e.: the synthesizer parameters estimation problem. We proposed a multi-modal deep-learning-based pipeline Sound2Synth, together with a network structure Prime-Dilated Convolution (PDC) specially designed to solve this problem. Our method achieved not only SOTA but also the first real-world applicable results on Dexed synthesizer, a popular FM synthesizer.

Norms help regulate a society. Norms may be explicit (represented in structured form) or implicit. We address the emergence of explicit norms by developing agents who provide and reason about explanations for norm violations in deciding sanctions and identifying alternative norms. These agents use a genetic algorithm to produce norms and reinforcement learning to learn the values of these norms. We find that applying explanations leads to norms that provide better cohesion and goal satisfaction for the agents. Our results are stable for societies with differing attitudes of generosity.

To avoid discriminatory uses of their data, organizations can learn to map them into a representation that filters out information related to sensitive attributes. However, all existing methods in fair representation learning generate a fairness-information trade-off. To achieve different points on the fairness-information plane, one must train different models. In this paper, we first demonstrate that fairness-information trade-offs are fully characterized by rate-distortion trade-offs. Then, we use this key result and propose SoFaiR, a single shot fair representation learning method that generates with one trained model many points on the fairness-information plane. Besides its computational saving, our single-shot approach is, to the extent of our knowledge, the first fair representation learning method that explains what information is affected by changes in the fairness / distortion properties of the representation. Empirically, we find on three datasets that SoFaiR achieves similar fairness information trade-offs as its multi-shot counterparts.

Manufacturing is transitioning from a mass production model to a service model in which facilities `bid' for previously unseen products. To decide whether to bid for a previously unseen product, a facility must be able to synthesize, on the fly, a process plan controller that delegates abstract manufacturing tasks in a supplied process recipe to the available manufacturing resources. First-order representations of the state are commonly considered in reasoning about action in AI. Here we show that we can leverage the wide literature on the Situation Calculus automatically synthesize such controllers. We identify two important decidable cases---finite domains and bounded action theories---for which we provide practical synthesis techniques.

We consider opinion diffusion for undirected networks with sequential updates when the opinions of the agents are single-peaked preference rankings. Our starting point is the study of preserving single-peakedness. We identify voting rules that, when given a single-peaked profile, output at least one ranking that is single peaked w.r.t. a single-peaked axis of the input. For such voting rules we show convergence to a stable state of the diffusion process that uses the voting rule as the agents' update rule. Further, we establish an efficient algorithm that maximises the spread of extreme opinions.

We study the extension of non-monotonic disjunctive logic programs with terms that represent sets of constants, called DLP(S), under the stable model semantics. This strictly increases expressive power, but keeps reasoning decidable, though cautious entailment is coNEXPTIME^NP-complete, even for data complexity. We present two new reasoning methods for DLP(S): a semantics-preserving translation of DLP(S) to logic programming with function symbols, which can take advantage of lazy grounding techniques, and a ground-and-solve approach that uses non-monotonic existential rules in the grounding stage. Our evaluation considers problems of ontological reasoning that are not in scope for traditional ASP (unless EXPTIME =ΠP2 ), and we find that our new existential-rule grounding performs well in comparison with native implementations of set terms in ASP.

Relational graph neural networks have garnered particular attention to encode graph context in knowledge graphs (KGs). Although they achieved competitive performance on small KGs, how to efficiently and effectively utilize graph context for large KGs remains an open problem. To this end, we propose the Relation-based Embedding Propagation (REP) method. It is a post-processing technique to adapt pre-trained KG embeddings with graph context. As relations in KGs are directional, we model the incoming head context and the outgoing tail context separately. Accordingly, we design relational context functions with no external parameters. Besides, we use averaging to aggregate context information, making REP more computation-efficient. We theoretically prove that such designs can avoid information distortion during propagation. Extensive experiments also demonstrate that REP has significant scalability while improving or maintaining prediction quality. Particularly, it averagely brings about 10% relative improvement to triplet-based embedding methods on OGBL-WikiKG2 and takes 5%-83% time to achieve comparable results as the state-of-the-art GC-OTE.

Recent advances in skeleton-based person re-identification (re-ID) obtain impressive performance via either hand-crafted skeleton descriptors or skeleton representation learning with deep learning paradigms. However, they typically require skeletal pre-modeling and label information for training, which leads to limited applicability of these methods. In this paper, we focus on unsupervised skeleton-based person re-ID, and present a generic Simple Masked Contrastive learning (SimMC) framework to learn effective representations from unlabeled 3D skeletons for person re-ID. Specifically, to fully exploit skeleton features within each skeleton sequence, we first devise a masked prototype contrastive learning (MPC) scheme to cluster the most typical skeleton features (skeleton prototypes) from different subsequences randomly masked from raw sequences, and contrast the inherent similarity between skeleton features and different prototypes to learn discriminative skeleton representations without using any label. Then, considering that different subsequences within the same sequence usually enjoy strong correlations due to the nature of motion continuity, we propose the masked intra-sequence contrastive learning (MIC) to capture intra-sequence pattern consistency between subsequences, so as to encourage learning more effective skeleton representations for person re-ID. Extensive experiments validate that the proposed SimMC outperforms most state-of-the-art skeleton-based methods. We further show its scalability and efficiency in enhancing the performance of existing models. Our codes are available at https://github.com/Kali-Hac/SimMC.

Spiking Neural Networks (SNNs) are receiving increasing attention due to their biological plausibility and the potential for ultra-low-power event-driven neuromorphic hardware implementation. Due to the complex temporal dynamics and discontinuity of spikes, training SNNs directly usually suffers from high computing resources and a long training time. As an alternative, SNN can be converted from a pre-trained artificial neural network (ANN) to bypass the difficulty in SNNs learning. However, the existing ANN-to-SNN methods neglect the inconsistency of information transmission between synchronous ANNs and asynchronous SNNs. In this work, we first analyze how the asynchronous spikes in SNNs may cause conversion errors between ANN and SNN. To address this problem, we propose a signed neuron with memory function, which enables almost no accuracy loss during the conversion process, and maintains the properties of asynchronous transmission in the converted SNNs. We further propose a new normalization method, named neuron-wise normalization, to significantly shorten the inference latency in the converted SNNs. We conduct experiments on challenging datasets including CIFAR10 (95.44% top-1), CIFAR100 (78.3% top-1) and ImageNet (73.16% top-1). Experimental results demonstrate that the proposed method outperforms the state-of-the-art works in terms of accuracy and inference time. The code is available at https://github.com/ppppps/ANN2SNNConversion_SNM_NeuronNorm.

Through this paper, we seek to reduce the communication barrier between the hearing-impaired community and the larger society who are usually not familiar with sign language in the sub-Saharan region of Africa with the largest occurrences of hearing disability cases, while using Nigeria as a case study. The dataset is a pioneer dataset for the Nigerian Sign Language and was created in collaboration with relevant stakeholders. We pre-processed the data in readiness for two different object detection models and a classification model and employed diverse evaluation metrics to gauge model performance on sign-language to text conversion tasks. Finally, we convert the predicted sign texts to speech and deploy the best performing model in a lightweight application that works in real-time and achieves impressive results converting sign words/phrases to text and subsequently, into speech.

Federated learning (FL) enables multiple clients to collaboratively train an accurate global model while protecting clients' data privacy. However, FL is susceptible to Byzantine attacks from malicious participants. Although the problem has gained significant attention, existing defenses have several flaws: the server irrationally chooses malicious clients for aggregation even after they have been detected in previous rounds; the defenses perform ineffectively against sybil attacks or in the heterogeneous data setting. To overcome these issues, we propose MAB-RFL, a new method for robust aggregation in FL. By modelling the client selection as an extended multi-armed bandit (MAB) problem, we propose an adaptive client selection strategy to choose honest clients that are more likely to contribute high-quality updates. We then propose two approaches to identify malicious updates from sybil and non-sybil attacks, based on which rewards for each client selection decision can be accurately evaluated to discourage malicious behaviors. MAB-RFL achieves a satisfying balance between exploration and exploitation on the potential benign clients. Extensive experimental results show that MAB-RFL outperforms existing defenses in three attack scenarios under different percentages of attackers.

We consider shared autonomy systems where multiple operators (AI and human), can interact with the environment, e.g. by controlling a robot. The decision problem for the shared autonomy system is to select which operator takes control at each timestep, such that a reward specifying the intended system behaviour is maximised. The performance of the human operator is influenced by unobserved factors, such as fatigue or skill level. Therefore, the system must reason over stochastic models of operator performance. We present a framework for stochastic operators in shared autonomy systems (SO-SAS), where we represent operators using rich, partially observable models. We formalise SO-SAS as a mixed-observability Markov decision process, where environment states are fully observable and internal operator states are hidden. We test SO-SAS on a simulated domain and a computer game, empirically showing it results in better performance compared to traditional formulations of shared autonomy systems.