IJCAI 2020 Papers

We present a novel high fidelity 3-D simulator that significantly reduces the sim-to-real gap for collision avoidance in dense crowds using Deep Reinforcement Learning (DRL). Our simulator models realistic crowd and pedestrian behaviors, along with friction, sensor noise and delays in the simulated robot model. We also describe a technique to incrementally control the randomness and complexity of training scenarios to achieve better convergence and generalization capabilities. We demonstrate the effectiveness of our simulator by training a policy that fuses data from multiple perception sensors such as a 2-D lidar and a depth camera to detect pedestrians and computes smooth, collision-free velocities. Our novel reward function and multi-sensor formulation results in smooth and unobtrusive navigation. We have evaluated the learned policy on two differential drive robots and evaluate its performance in new dense crowd scenarios, narrow corridors, T and L-junctions, etc. We observe that our algorithm outperforms prior dynamic navigation techniques in terms of metrics such as success rate, trajectory length, mean time to goal, and smoothness.

Deep convolutional neural networks (DCNNs) have contributed many breakthroughs in segmentation tasks, especially in the field of medical imaging. However, domain shift and corrupted annotations, which are two common problems in medical imaging, dramatically degrade the performance of DCNNs in practice. In this paper, we propose a novel robust cross-denoising framework using two peer networks to address domain shift and corrupted label problems with a peer-review strategy. Specifically, each network performs as a mentor, mutually supervised to learn from reliable samples selected by the peer network to combat with corrupted labels. In addition, a noise-tolerant loss is proposed to encourage the network to capture the key location and filter the discrepancy under various noise-contaminant labels. To further reduce the accumulated error, we introduce a class-imbalanced cross learning using most confident predictions at class-level. Experimental results on REFUGE and Drishti-GS datasets for optic disc (OD) and optic cup (OC) segmentation demonstrate the superior performance of our proposed approach to the state-of-the-art methods.

Predicting anomalies (e.g., blocked driveway and vehicle collisions) in urban space plays an important role in assisting governments and communities for building smart city applications, ranging from intelligent transportation to public safety. However, predicting urban anomalies is not trivial due to the following two factors: i) The sequential transition regularities of anomaly occurrences is complex, which exhibit with high-order and dynamic correlations. ii) The Interactions between region, time and anomaly category is multi-dimensional in real-world urban anomaly forecasting scenario. How to fuse multiple relations from spatial, temporal and categorical dimensions in the predictive framework remains a significant challenge. To address these two challenges, we propose a Cross-Interaction Hierarchical Attention network model (CHAT) which uncovers the dynamic occurrence patterns of time-stamped urban anomaly data. Our CHAT framework could automatically capture the relevance of past anomaly occurrences across different time steps, and discriminates which types of cross-modal interactions are more important for making future predictions. Experiment results demonstrate the superiority of CHAT framework over state-of-the-art baselines.

Counting answers to a query is an operation supported by virtually all database management systems. In this paper we focus on counting answers over a Knowledge Base (KB), which may be viewed as a database enriched with background knowledge about the domain under consideration. In particular, we place our work in the context of Ontology-Mediated Query Answering/Ontology-based Data Access (OMQA/OBDA), where the language used for the ontology is a member of the DL-Lite family and the data is a (usually virtual) set of assertions. We study the data complexity of query answering, for different members of the DL-Lite family that include number restrictions, and for variants of conjunctive queries with counting that differ with respect to their shape (connected, branching, rooted). We improve upon existing results by providing PTIME and coNP lower bounds, and upper bounds in PTIME and LOGSPACE. For the LOGSPACE case, we have devised a novel query rewriting technique into first-order logic with counting.

Cost partitioning is a method for admissibly combining admissible heuristics. In this work, we extend this concept to merge-and-shrink (M&S) abstractions that may use labels that do not directly correspond to operators. We investigate how optimal and saturated cost partitioning (SCP) interact with M&S transformations and develop a method to compute SCPs during the computation of M&S. Experiments show that SCP significantly improves M&S on standard planning benchmarks.

Bug localization plays an important role in software quality control. Many supervised machine learning models have been developed based on historical bug-fix information. Despite being successful, these methods often require sufficient historical data (i.e., labels), which is not always available especially for newly developed software projects. In response, cross-project bug localization techniques have recently emerged whose key idea is to transferring knowledge from label-rich source project to locate bugs in the target project. However, a major limitation of these existing techniques lies in that they fail to capture the specificity of each individual project, and are thus prone to negative transfer. To address this issue, we propose an adversarial transfer learning bug localization approach, focusing on only transferring the common characteristics (i.e., public information) across projects. Specifically, our approach (CooBa) learns the indicative public information from cross-project bug reports through a shared encoder, and extracts the private information from code files by an individual feature extractor for each project. CooBa further incorporates adversarial learning mechanism to ensure that public information shared between multiple projects could be effectively extracted. Extensive experiments on four large-scale real-world data sets demonstrate that the proposed CooBa significantly outperforms the state of the art techniques.

To reliably detect out-of-distribution images based on already deployed convolutional neural networks, several recent studies on the out-of-distribution detection have tried to define effective confidence scores without retraining the model. Although they have shown promising results, most of them need to find the optimal hyperparameter values by using a few out-of-distribution images, which eventually assumes a specific test distribution and makes it less practical for real-world applications. In this work, we propose a novel out-of-distribution detection method termed as MALCOM, which neither uses any out-of-distribution sample nor retrains the model. Inspired by an observation that the global average pooling cannot capture spatial information of feature maps in convolutional neural networks, our method aims to extract informative sequential patterns from the feature maps. To this end, we introduce a similarity metric that focuses on shared patterns between two sequences based on the normalized compression distance. In short, MALCOM uses both the global average and the spatial patterns of feature maps to identify out-of-distribution images accurately.

The b-matching game is a cooperative game defined on a graph. The game generalizes the matching game to allow each individual to have more than one partner. The game has several applications, such as the roommate assignment, the multi-item version of the seller-buyer assignment, and the international kidney exchange. Compared with the standard matching game, the b-matching game is computationally hard. In particular, the core non-emptiness problem and the core membership problem are co-NP-hard. Therefore, we focus on the convexity of the game, which is a sufficient condition of the core non-emptiness and often more tractable concept than the core non-emptiness. It also has several additional benefits. In this study, we give a necessary and sufficient condition of the convexity of the b-matching game. This condition also gives an O(n log n + m α(n)) time algorithm to determine whether a given game is convex or not, where n and m are the number of vertices and edges of a given graph, respectively, and α(・) is the inverse-Ackermann function. Using our characterization, we also give a polynomial-time algorithm to compute the Shapley value of a convex b-matching game.

We study privacy-preserving query answering in Description Logics (DLs). Specifically, we consider the approach of controlled query evaluation (CQE) based on the notion of instance indistinguishability. We derive data complexity results for query answering over DL-LiteR ontologies, through a comparison with an alternative, existing confidentiality-preserving approach to CQE. Finally, we identify a semantically well-founded notion of approximated query answering for CQE, and prove that, for DL-LiteR ontologies, this form of CQE is tractable with respect to data complexity and is first-order rewritable, i.e., it is always reducible to the evaluation of a first-order query over the data instance.

Control argumentation frameworks (CAFs) allow for modeling uncertainties inherent in various argumentative settings. We establish a complete computational complexity map of the central computational problem of controllability in CAFs for five key semantics. We also develop Boolean satisfiability based counterexample-guided abstraction refinement algorithms and direct encodings of controllability as quantified Boolean formulas, and empirically evaluate their scalability on a range of NP-hard variants of controllability.

Point-of-interest (POI) recommendation has become an increasingly important sub-field of recommendation system research. Previous methods employ various assumptions to exploit the contextual information for improving the recommendation accuracy. The common property among them is that similar users are more likely to visit similar POIs and similar POIs would like to be visited by the same user. However, none of existing methods utilize similarity explicitly to make recommendations. In this paper, we propose a new framework for POI recommendation, which explicitly utilizes similarity with contextual information. Specifically, we categorize the context information into two groups, i.e., global and local context, and develop different regularization terms to incorporate them for recommendation. A graph Laplacian regularization term is utilized to exploit the global context information. Moreover, we cluster users into different groups, and let the objective function constrain the users in the same group to have similar predicted POI ratings. An alternating optimization method is developed to optimize our model and get the final rating matrix. The results in our experiments show that our algorithm outperforms all the state-of-the-art methods.

This paper takes a step towards the theoretical analysis of the relationship between word embeddings and context embeddings in models such as word2vec. We start from basic probabilistic assumptions on the nature of word vectors, context vectors, and text generation. These assumptions are supported either empirically or theoretically by the existing literature. Next, we show that under these assumptions the widely-used word-word PMI matrix is approximately a random symmetric Gaussian ensemble. This, in turn, implies that context vectors are reflections of word vectors in approximately half the dimensions. As a direct application of our result, we suggest a theoretically grounded way of tying weights in the SGNS model.

Context modeling helps understand the data, such as sentence or user behavior. Contextual information captures the important underlying feature, and it enhances the relationship between data instances or hidden representations. As the importance of the sequential model grows, so does the importance of the sequential contextual modeling. Under the sequential data, we need to consider the context change over time. In this paper, we present our research works on context modeling and its dynamics modeling over time. Furthermore, we extend our research to handle the multi-granularity of sequential context modeling to consider rich context representations.

We propose a policy improvement algorithm for Reinforcement Learning (RL) termed Rerouted Behavior Improvement (RBI). RBI is designed to take into account the evaluation errors of the Q-function. Such errors are common in RL when learning the Q-value from finite experience data. Greedy policies or even constrained policy optimization algorithms that ignore these errors may suffer from an improvement penalty (i.e., a policy impairment). To reduce the penalty, the idea of RBI is to attenuate rapid policy changes to actions that were rarely sampled. This approach is shown to avoid catastrophic performance degradation and reduce regret when learning from a batch of transition samples. Through a two-armed bandit example, we show that it also increases data efficiency when the optimal action has a high variance. We evaluate RBI in two tasks in the Atari Learning Environment: (1) learning from observations of multiple behavior policies and (2) iterative RL. Our results demonstrate the advantage of RBI over greedy policies and other constrained policy optimization algorithms both in learning from observations and in RL tasks.

In the few-shot learning scenario, the data-distribution discrepancy between training data and test data in a task usually exists due to the limited data. However, most existing meta-learning approaches seldom consider this intra-task discrepancy in the meta-training phase which might deteriorate the performance. To overcome this limitation, we develop a new consistent meta-regularization method to reduce the intra-task data-distribution discrepancy. Moreover, the proposed meta-regularization method could be readily inserted into existing optimization-based meta-learning models to learn better meta-knowledge. Particularly, we provide the theoretical analysis to prove that using the proposed meta-regularization, the conventional gradient-based meta-learning method can reach the lower regret bound. The extensive experiments also demonstrate the effectiveness of our method, which indeed improves the performances of the state-of-the-art gradient-based meta-learning models in the few-shot classification task.

2D image-based 3D objects retrieval is a new topic for 3D objects retrieval which can be used to manage 3D data with 2D images. The goal is to search some related 3D objects when given a 2D image. The task is challenging due to the large domain gap between 2D images and 3D objects. Therefore, it is essential to consider domain adaptation problems to reduce domain discrepancy. However, most of the existing domain adaptation methods only utilize the semantic information from the source domain to predict labels in the target domain and neglect the intrinsic structure of the target domain. In this paper, we propose a domain alignment framework with consistent domain structure learning to reduce the large gap between 2D images and 3D objects. The domain structure learning module makes use of both the semantic information from the source domain and the intrinsic structure of the target domain, which provides more reliable predicted labels to the domain alignment module to better align the conditional distribution. We conducted experiments on two public datasets, MI3DOR and MI3DOR-2, and the experimental results demonstrate the proposed method outperforms the state-of-the-art methods.

This paper presents an embedding of ontologies expressed in the ALC description logic into a real-valued vector space, comprising restricted existential and universal quantifiers, as well as concept negation and concept disjunction. Our main result states that an ALC ontology is satisfiable in the classical sense iff it is satisfiable by a partial faithful geometric model based on cones. The line of work to which we contribute aims to integrate knowledge representation techniques and machine learning. The new cone-model of ALC proposed in this work gives rise to conic optimization techniques for machine learning, extending previous approaches by its ability to model full ALC.

Action models of Dynamic Epistemic Logic (DEL) represent precisely how actions are perceived by agents. DEL has recently been used to define infinite multi-player games, and it was shown that they can be solved in some cases. However, the dynamics being defined by the classic DEL update product for individual actions, only turn-based games have been considered so far. In this work we define a concurrent DEL product, propose a mechanism to resolve conflicts between actions, and define concurrent DEL games. As in the turn-based case, the obtained concurrent infinite game arenas can be finitely represented when all actions are public, or all are propositional. Thus we identify cases where the strategic epistemic logic ATL*K can be model checked on such games.

We study higher statistical moments of Distortion for randomized social choice in a metric implicit utilitarian model. The Distortion of a social choice mechanism is the expected approximation factor with respect to the optimal utilitarian social cost (OPT). The k'th moment of Distortion is the expected approximation factor with respect to the k'th power of OPT. We consider mechanisms that elicit alternatives by randomly sampling voters for their favorite alternative. We design two families of mechanisms that provide constant (with respect to the number of voters and alternatives) k'th moment of Distortion using just k samples if all voters can then participate in a vote among the proposed alternatives, or 2k-1 samples if only the sampled voters can participate. We also show that these numbers of samples are tight. Such mechanisms deviate from a constant approximation to OPT with probability that drops exponentially in the number of samples, independent of the total number of voters and alternatives. We conclude with simulations on real-world Participatory Budgeting data to qualitatively complement our theoretical insights.